© 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. 4-CLT-HP
    7. 293
    Prev
    Next
    INDEX
    Explanations

    for

    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
    ReusableCell
    -0.73
    NameInMap
    -0.68
    Демографія
    -0.65
    ArrowToggle
    -0.61
     stay
    -0.59
     ddelweddau
    -0.59
    TypedDataSet
    -0.57
     Stay
    -0.56
     stays
    -0.55
     himo
    -0.53
    POSITIVE LOGITS
     désolés
    0.58
    exprimer
    0.58
     moindre
    0.57
     clearColor
    0.56
    
    0.56
    artige
    0.55
     to
    0.54
    moiselle
    0.54
     sehari
    0.52
     arvio
    0.52
    Activations Density 0.003%

    No Known Activations