© 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. 15733
    Prev
    Next
    INDEX
    Explanations

    dentistry

    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
    atina
    -0.48
     Superhosts
    -0.43
    pagest
    -0.41
    äiv
    -0.41
    atai
    -0.41
     "$@"
    -0.40
    ModelAdmin
    -0.40
    irsk
    -0.39
    ikh
    -0.39
    ="{{
    -0.39
    POSITIVE LOGITS
     հղումներ
    0.69
    migrationBuilder
    0.63
     للمعارف
    0.63
    EDEFAULT
    0.63
    cloudflare
    0.61
     dAtA
    0.61
    ंदीखरीदारी
    0.60
     समीक्षक
    0.60
    WindowConstants
    0.60
     урна
    0.59
    Activations Density 0.021%

    No Known Activations