© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 7825
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .s followed by sort (negative activations)

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ].
    -0.07
    <|
    -0.07
    lse
    -0.06
     main
    -0.05
     as
    -0.04
     solve
    -0.03
     run
    -0.03
    main
    -0.03
     True
    -0.03
    -0.03
    POSITIVE LOGITS
     directions
    0.04
    class
    0.03
    .b
    0.03
     value
    0.02
     B
    0.02
     max
    0.02
    O
    0.02
    ink
    0.01
     name
    0.01
    def
    0.01
    Activations Density 97.483%

    No Known Activations