© 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. 14084
    Prev
    Next
    INDEX
    Explanations

    said

    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
    WithMany
    -0.86
    adaptiveStyles
    -0.80
    TypedDataSet
    -0.74
    
    -0.71
    はじめに
    -0.64
    ArgsConstructor
    -0.61
     EconPapers
    -0.58
    RectangleBorder
    -0.57
    SharedDtor
    -0.57
     Réponses
    -0.57
    POSITIVE LOGITS
    );"
    0.59
     lourdes
    0.57
    ()]);
    0.54
     enkelt
    0.54
    dificio
    0.53
     positifs
    0.53
     pauvres
    0.51
     singoli
    0.51
    )';
    0.51
    KIND
    0.51
    Activations Density 0.056%

    No Known Activations