© 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. 20-CLT-HP
    7. 77848
    Prev
    Next
    INDEX
    Explanations

    potentially events/politics

    np_max-act-logits · 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
     المعيارى
    -0.86
     виправивши
    -0.79
    出版年
    -0.69
    SuppressLint
    -0.69
    DockStyle
    -0.68
    CppMethod
    -0.66
     saites
    -0.65
    enosis
    -0.65
     Infórmanos
    -0.65
    !*\
    -0.65
    POSITIVE LOGITS
     pot
    0.52
     ModelExpression
    0.47
     salted
    0.45
    pot
    0.44
     đoán
    0.43
    ubert
    0.42
     tension
    0.41
     stock
    0.41
     Stock
    0.40
    forsk
    0.40
    Activations Density 0.000%

    No Known Activations