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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14243
    Prev
    Next
    INDEX
    Explanations

    of

    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
    tvguidetime
    -0.85
    出版年
    -0.81
    ViewImports
    -0.77
     resourceCulture
    -0.77
    帖最后由
    -0.75
    Lähteet
    -0.69
    enterOuterAlt
    -0.68
    rungsseite
    -0.67
    Personendaten
    -0.67
    Rüyada
    -0.66
    POSITIVE LOGITS
    NetCore
    0.43
    keted
    0.41
     
    0.40
    tempts
    0.37
    isome
    0.36
    unnitel
    0.36
    kozá
    0.36
    場所は
    0.36
    ifiable
    0.34
    ividual
    0.34
    Activations Density 0.006%

    No Known Activations