© 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. 4-CLT-HP
    7. 993
    Prev
    Next
    INDEX
    Explanations

    software code and instructions

    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
    TagMode
    -0.66
     HasFactory
    -0.62
     Sociales
    -0.60
     igång
    -0.57
    providedIn
    -0.57
    migrationBuilder
    -0.55
     بيها
    -0.55
    HasForeignKey
    -0.54
     Partici
    -0.53
     navideños
    -0.53
    POSITIVE LOGITS
     tắt
    0.62
    <bos>
    0.56
    aches
    0.49
     Wikimedijinoj
    0.49
    oredCriteria
    0.47
    UiThread
    0.44
    hésite
    0.44
    клопе
    0.44
    ждый
    0.44
     hitch
    0.43
    Activations Density 0.006%

    No Known Activations