© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2290
    Prev
    Next
    INDEX
    Explanations

    Instructions and links

    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
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -0.72
     about
    -0.53
     showing
    -0.47
     all
    -0.46
     looking
    -0.45
     not
    -0.45
     of
    -0.44
     for
    -0.42
     a
    -0.42
     recognizing
    -0.41
    POSITIVE LOGITS
     للمعارف
    0.96
    windowFixed
    0.94
     AssemblyCulture
    0.93
     تضيفلها
    0.88
     Paglinawan
    0.83
     surla
    0.81
    UrlResolution
    0.81
    GEBURTS
    0.81
    脚注の使い方
    0.79
    AccessorTable
    0.77
    Activations Density 0.000%

    No Known Activations