© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3144
    Prev
    Next
    INDEX
    Explanations

    treatment effectiveness

    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
    robes
    -0.46
     to
    -0.43
    gou
    -0.42
     coff
    -0.40
    Duck
    -0.40
    ডি
    -0.39
    engi
    -0.38
    usias
    -0.38
     chinh
    -0.38
    หาร
    -0.37
    POSITIVE LOGITS
     OFDb
    0.91
    twimg
    0.85
    mybatisplus
    0.80
     שוליים
    0.79
    StoryboardSegue
    0.78
     ModelExpression
    0.77
    ScopeManager
    0.74
    RenderAtEndOf
    0.74
    GraphicsUnit
    0.74
     للاسماء
    0.71
    Activations Density 0.008%

    No Known Activations