© 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. 0-CLT-HP
    7. 93491
    Prev
    Next
    INDEX
    Explanations

    Judge

    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
     judge
    -1.27
     justice
    -1.16
    justice
    -1.16
     Justice
    -1.15
     Judge
    -1.13
    Justice
    -1.09
    Judge
    -1.02
    judge
    -0.96
     JUDGE
    -0.94
     JUSTICE
    -0.86
    POSITIVE LOGITS
    AutoScaleMode
    0.83
     Theſe
    0.82
     poffe
    0.81
     itſelf
    0.80
     ſeveral
    0.79
     Efq
    0.78
     للمعارف
    0.75
     Monfieur
    0.74
     whoſe
    0.73
     الرياضيه
    0.71
    Activations Density 0.133%

    No Known Activations