© 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. 4-CLT-HP
    7. 1878
    Prev
    Next
    INDEX
    Explanations

    about

    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
    aktery
    -0.53
    UniformLocation
    -0.52
    ού
    -0.51
    acor
    -0.50
    askin
    -0.50
    handleDelete
    -0.49
    IENTE
    -0.49
    zzlies
    -0.49
     pure
    -0.48
    SqlClient
    -0.48
    POSITIVE LOGITS
     للمعارف
    0.92
     ostavi
    0.83
    出版年
    0.69
    Istorija
    0.67
     resourceCulture
    0.66
     HttpNotFound
    0.65
    ThroughAttribute
    0.64
    Šaltiniai
    0.63
    ContentAlignment
    0.61
     cherchés
    0.60
    Activations Density 0.002%

    No Known Activations