© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11323
    Prev
    Next
    INDEX
    Explanations

    visible transparent

    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
    SharedCtor
    -0.90
     ModelExpression
    -0.79
    KommentareTeilen
    -0.78
     Efq
    -0.71
     themſelves
    -0.71
     neceff
    -0.71
     fubject
    -0.69
     myſelf
    -0.69
     &___
    -0.68
     Anſ
    -0.68
    POSITIVE LOGITS
     Haus
    0.42
     متعلقه
    0.40
     Tra
    0.39
    yen
    0.37
    glfw
    0.36
    nacht
    0.36
     Han
    0.36
    教科
    0.36
     gas
    0.36
    لاعب
    0.35
    Activations Density 0.016%

    No Known Activations