© 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. 6070
    Prev
    Next
    INDEX
    Explanations

    code-related text

    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
    CloseOperation
    -0.73
    Totale
    -0.68
    Geplaatst
    -0.65
    rrggbb
    -0.56
    ValueStyle
    -0.52
    ViewFeatures
    -0.52
    脚注の使い方
    -0.50
    __);
    -0.50
    InitVars
    -0.50
    Становништво
    -0.49
    POSITIVE LOGITS
    ⓧ
    0.56
    erva
    0.52
     Emerald
    0.51
     Muro
    0.50
     Reinh
    0.50
     Medina
    0.50
     Merv
    0.50
    IonicModule
    0.49
    MessageOf
    0.48
     PRD
    0.48
    Activations Density 0.021%

    No Known Activations