© 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. 16223
    Prev
    Next
    INDEX
    Explanations

    year

    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
     الحره
    -0.64
    /*
    -0.57
     correctes
    -0.56
    ***************/
    -0.55
     RoutedEventArgs
    -0.54
     '\\;'
    -0.51
    Примечания
    -0.50
    CloseOperation
    -0.50
    :✨
    -0.50
    lanze
    -0.50
    POSITIVE LOGITS
    RTCK
    0.66
    MENAFN
    0.52
     BoxDecoration
    0.50
     sandalias
    0.49
     незавершена
    0.48
     parliament
    0.48
    erape
    0.47
    KommentareTeilen
    0.47
    dflare
    0.47
    osoever
    0.47
    Activations Density 0.052%

    No Known Activations