© 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. 93181
    Prev
    Next
    INDEX
    Explanations

    legal and law enforcement

    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
     sent
    -0.80
     criticised
    -0.73
     criticized
    -0.63
    djangoproject
    -0.59
     trekken
    -0.57
    enumi
    -0.56
     apologised
    -0.56
     sued
    -0.56
     déclaré
    -0.55
     urged
    -0.54
    POSITIVE LOGITS
     Monfieur
    1.16
     pleaſure
    1.13
     myſelf
    1.03
     Anſ
    1.00
     Diſ
    0.99
     Majefty
    0.99
     ſeveral
    0.96
     itſelf
    0.96
     ſche
    0.93
     ſever
    0.92
    Activations Density 0.065%

    No Known Activations