© 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. 8055
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    beginning of a function definition (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
    s
    -0.04
    prese
    -0.03
     represent
    -0.03
     contain
    -0.03
    anage
    -0.02
     has
    -0.02
    ns
    -0.02
    put
    -0.02
    section
    -0.02
    ure
    -0.01
    POSITIVE LOGITS
    ram
    0.02
    ases
    0.02
    tic
    0.01
    ath
    0.01
    ates
    0.01
     cont
    0.01
    ays
    0.01
    tes
    0.01
    olution
    0.01
    '
    0.00
    Activations Density 90.729%

    No Known Activations