© 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. 7960
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    comma or colon after numbers in lists/ranges

    python-code · gemini-2.5-flash-lite

    .grid calls with column and row arguments (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
    gest
    -0.02
    valu
    -0.02
    [j
    -0.02
    area
    -0.02
    _for
    -0.02
    |
    -0.02
    our
    -0.02
    team
    -0.02
    (w
    -0.02
    raw
    -0.02
    POSITIVE LOGITS
    _route
    0.05
    _routes
    0.04
    _tree
    0.04
    _solution
    0.04
    _population
    0.03
    _move
    0.03
    _room
    0.03
     continue
    0.03
    _si
    0.03
    _conne
    0.03
    Activations Density 100.000%

    No Known Activations