© 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. 5-CLT-HP
    7. 91733
    Prev
    Next
    INDEX
    Explanations

    h

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    -0.63
    InitVars
    -0.56
    Jeografia
    -0.54
    ：
    -0.53
     {?>
    -0.53
    plish
    -0.50
    /
    -0.50
    :`
    -0.49
     :
    -0.49
    EDEFAULT
    -0.48
    POSITIVE LOGITS
     protoimpl
    0.60
     InputDecoration
    0.59
    RenderAtEndOf
    0.57
    neſs
    0.54
    RuleContext
    0.54
    λεί
    0.54
     pleaſure
    0.53
     relax
    0.52
    σμο
    0.52
    ArgsConstructor
    0.52
    Activations Density 0.001%

    No Known Activations