© 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. 0-CLT-HP
    7. 97354
    Prev
    Next
    INDEX
    Explanations

    layer

    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
     للمعارف
    -1.02
     layer
    -1.01
     فريبيس
    -0.97
    layer
    -0.95
     ब्रेकडाउन
    -0.95
    المناصب
    -0.93
    مصادر
    -0.91
     LAYER
    -0.90
    GraphicsUnit
    -0.90
     للاسماء
    -0.88
    POSITIVE LOGITS
     pageNo
    0.55
     pageNumber
    0.46
    cheid
    0.43
    rho
    0.43
     postId
    0.42
    .
    0.42
     ret
    0.41
     T
    0.41
    leg
    0.40
     annex
    0.40
    Activations Density 0.267%

    No Known Activations