© 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. 0-CLT-HP
    7. 94936
    Prev
    Next
    INDEX
    Explanations

    domin

    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
    ly
    -0.69
    ness
    -0.56
    了
    -0.55
    nya
    -0.55
    day
    -0.54
    🏻
    -0.52
     EClass
    -0.52
    ों
    -0.50
    nage
    -0.49
    ERY
    -0.48
    POSITIVE LOGITS
     pleaſure
    1.03
     ſche
    0.92
     itſelf
    0.91
     raiſ
    0.91
     purpoſe
    0.89
     myſelf
    0.87
     Jefus
    0.86
     poffible
    0.84
    migrationBuilder
    0.84
     Reſ
    0.82
    Activations Density 0.185%

    No Known Activations