© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6006
    Prev
    Next
    INDEX
    Explanations

    ;

    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
    </strong>
    -0.48
    ונות
    -0.47
    </h3>
    -0.47
    </blockquote>
    -0.46
    </h1>
    -0.46
    SDL
    -0.46
    nian
    -0.45
    ,
    -0.43
    клопе
    -0.43
    PTI
    -0.42
    POSITIVE LOGITS
     beginnetje
    0.91
    AnchorStyles
    0.87
     للاسماء
    0.86
    WithMany
    0.81
     kasarigan
    0.81
     CreateTagHelper
    0.77
    OGND
    0.68
    RenderAtEndOf
    0.65
    TextWatcher
    0.65
    //
    0.63
    Activations Density 0.082%

    No Known Activations