© 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. 1-CLT-HP
    7. 9328
    Prev
    Next
    INDEX
    Explanations

    legal judgments

    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
     frå
    -0.43
     calcetines
    -0.42
     court
    -0.41
    djangoproject
    -0.40
    ան
    -0.40
     ModelExpression
    -0.38
    ulitan
    -0.37
    porque
    -0.36
    jsxFileName
    -0.35
    wahl
    -0.35
    POSITIVE LOGITS
    Diweddarwch
    0.85
    脚注の使い方
    0.84
     myſelf
    0.81
     neceffary
    0.80
     raiſ
    0.77
     Jefus
    0.76
     uſed
    0.73
     themſelves
    0.73
     whoſe
    0.73
     تضيفلها
    0.72
    Activations Density 0.357%

    No Known Activations