© 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. 0-CLT-HP
    7. 95617
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    ValueStyle
    -0.83
     Theſe
    -0.77
     ſeveral
    -0.72
     auffi
    -0.69
     poffe
    -0.69
     Anſ
    -0.68
     Shakspeare
    -0.68
     uſed
    -0.66
     purpoſe
    -0.64
     uſe
    -0.64
    POSITIVE LOGITS
    المراجع
    0.51
    }{*}{}
    0.50
    iegler
    0.48
     in
    0.46
    CompilerServices
    0.45
     Co
    0.45
    Sklici
    0.45
     comp
    0.44
    рення
    0.43
    OwnProperty
    0.43
    Activations Density 0.055%

    No Known Activations