© 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. 1-CLT-HP
    7. 16061
    Prev
    Next
    INDEX
    Explanations

    void

    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
    Negative Logits
     للاسماء
    -0.49
    redited
    -0.46
    例句
    -0.42
    DataAnnotations
    -0.42
     Rasen
    -0.40
     Hauptmann
    -0.40
    ppus
    -0.39
     Anlage
    -0.38
    unjung
    -0.38
    WebElementEntity
    -0.38
    POSITIVE LOGITS
    Ārējās
    0.70
     referenties
    0.68
     CGRectMake
    0.65
    Према
    0.65
     مشين
    0.63
    WriteTagHelper
    0.63
    __);
    0.62
    aarrggbb
    0.62
    PerformLayout
    0.61
    BeginContext
    0.59
    Activations Density 0.008%

    No Known Activations