© 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. 10025
    Prev
    Next
    INDEX
    Explanations

    legal, communications, medical

    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
     referenties
    -0.72
     Katz
    -0.66
    kwds
    -0.60
     Sche
    -0.57
    chemise
    -0.55
    atz
    -0.53
    qrstuvwxyz
    -0.52
    tomans
    -0.52
    protos
    -0.51
    CHARGE
    -0.50
    POSITIVE LOGITS
     pleaſure
    0.56
     perſon
    0.56
     ſche
    0.56
     houſe
    0.55
     ModelExpression
    0.55
     ſta
    0.55
     ſmall
    0.55
    تقاوى
    0.54
    EndInit
    0.54
     ſtre
    0.54
    Activations Density 0.286%

    No Known Activations