© 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. 20-CLT-HP
    7. 77744
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · 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
    :✨
    -0.68
    endmodule
    -0.59
    riotic
    -0.54
    kuuta
    -0.53
    uminense
    -0.50
    هایت
    -0.50
     autorytatywna
    -0.49
     itinéraires
    -0.48
    الإنجليزية
    -0.48
    andoah
    -0.47
    POSITIVE LOGITS
     مرئيه
    0.54
    GraphicsUnit
    0.50
     MainAxisSize
    0.50
     виправивши
    0.49
     WaitForSeconds
    0.49
     difficiles
    0.47
     snippetHide
    0.47
     Papst
    0.46
     MediatR
    0.45
     vielä
    0.45
    Activations Density 0.002%

    No Known Activations