© 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. 271
    Prev
    Next
    INDEX
    Explanations

    sixth

    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
    DoubleQuotes
    -0.88
     ModelExpression
    -0.82
     ***!
    -0.77
     Chwiliwch
    -0.71
    rungsseite
    -0.67
    SizeF
    -0.61
     للاسماء
    -0.60
    ReusableCell
    -0.60
     recev
    -0.59
     collectif
    -0.59
    POSITIVE LOGITS
    ']=$
    0.50
     different
    0.50
    ArrowToggle
    0.46
    OPINION
    0.45
     OPINION
    0.42
     instant
    0.41
    ']))
    0.41
     split
    0.41
    ^^^^^^^^
    0.41
    ื้อ
    0.41
    Activations Density 0.016%

    No Known Activations