# Interpreting neural computations by examining intrinsic and embedding dimensionality of neural activity

arXiv: https://arxiv.org/abs/2107.04084 · HTML: https://mlsanity.com/paper/2107.04084/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2021.

## Built on by (most cited first, 24 of 24)

- [Learnable latent embeddings for joint behavioral and neural analysis](https://mlsanity.com/paper/2204.00673/) (2022)
- [A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning](https://mlsanity.com/paper/2307.15092/) (2023)
- [Disentangling and Mitigating the Impact of Task Similarity for Continual Learning](https://mlsanity.com/paper/2405.20236/) (2024)
- [Geometric Signatures of Compositionality Across a Language Model's Lifetime](https://mlsanity.com/paper/2410.01444/) (2024)
- [A Spectral Theory of Neural Prediction and Alignment](https://mlsanity.com/paper/2309.12821/) (2023)
- [Neural population geometry and optimal coding of tasks with shared latent structure](https://mlsanity.com/paper/2402.16770/) (2024)
- [Learning shared neural manifolds from multi-subject FMRI data](https://mlsanity.com/paper/2201.00622/) (2021)
- [Expressive architectures enhance interpretability of dynamics-based neural population models](https://mlsanity.com/paper/2212.03771/) (2022)
- [Eight challenges in developing theory of intelligence](https://mlsanity.com/paper/2306.11232/) (2023)
- [Deep Learning Models to Study Sentence Comprehension in the Human Brain](https://mlsanity.com/paper/2301.06340/) (2023)
- [Contrastive Self-Supervised Learning As Neural Manifold Packing](https://mlsanity.com/paper/2506.13717/) (2025)
- [Divergent representations of ethological visual inputs emerge from supervised, unsupervised, and reinforcement learning](https://mlsanity.com/paper/2112.02027/) (2021)
- [Spiking mode-based neural networks](https://mlsanity.com/paper/2310.14621/) (2023)
- [Category learning in deep neural networks: Information content and geometry of internal representations](https://mlsanity.com/paper/2510.19021/) (2025)
- [Interpolation, extrapolation, and local generalization in common neural networks](https://mlsanity.com/paper/2207.08648/) (2022)
- [Statistical physics, Bayesian inference and neural information processing](https://mlsanity.com/paper/2309.17006/) (2023)
- [Information theoretic study of the neural geometry induced by category learning](https://mlsanity.com/paper/2311.15682/) (2023)
- [Input-driven circuit reconfiguration in critical recurrent neural networks](https://mlsanity.com/paper/2405.15036/) (2024)
- [Storing overlapping associative memories on latent manifolds in low-rank spiking networks](https://mlsanity.com/paper/2411.17485/) (2024)
- [Integration of Calcium Imaging Traces via Deep Generative Modeling](https://mlsanity.com/paper/2501.14615/) (2025)
- [Characterizing higher-order representations through generative diffusion models explains human decoded neurofeedback performance](https://mlsanity.com/paper/2503.14333/) (2025)
- [Embedding of Low-Dimensional Sensory Dynamics in Recurrent Networks: Implications for the Geometry of Neural Representation](https://mlsanity.com/paper/2601.19019/) (2026)
- [Spark: Modular Spiking Neural Networks](https://mlsanity.com/paper/2602.02306/) (2026)
- [Psychosis involves a deficit of information compression in connected speech](https://mlsanity.com/paper/2609.15522/) (2026)

## Abstract (arXiv)

The ongoing exponential rise in recording capacity calls for new approaches for analysing and interpreting neural data. Effective dimensionality has emerged as an important property of neural activity across populations of neurons, yet different studies rely on different definitions and interpretations of this quantity. Here we focus on intrinsic and embedding dimensionality, and discuss how they might reveal computational principles from data. Reviewing recent works, we propose that the intrinsic dimensionality reflects information about the latent variables encoded in collective activity, while embedding dimensionality reveals the manner in which this information is processed. We conclude by highlighting the role of network models as an ideal substrate for testing more specifically various hypotheses on the computational principles reflected through intrinsic and embedding dimensionality.