© 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. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11686
    Prev
    Next
    INDEX
    Explanations

    expressions involving derivatives of parameters in mathematical formulas

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getElementById
    -0.52
    벗
    -0.49
     >
    -0.49
    '];?>
    -0.49
     The
    -0.49
     "</
    -0.49
    yo
    -0.48
    The
    -0.48
     Where
    -0.47
     bort
    -0.47
    POSITIVE LOGITS
     Baillargeon
    1.02
    ruptedException
    0.93
    matchCondition
    0.92
     itſelf
    0.91
    etheless
    0.88
     للمعارف
    0.88
     Efq
    0.83
    GraphicsUnit
    0.83
    WebServlet
    0.79
     himſelf
    0.79
    Activations Density 0.005%

    No Known Activations