© 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. 1-CLT-HP
    7. 691
    Prev
    Next
    INDEX
    Explanations

    code

    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
     useParams
    -0.71
     XCTest
    -0.63
     onPostExecute
    -0.55
    RenderAtEndOf
    -0.54
     CommonModule
    -0.53
     lẻ
    -0.52
    UnusedPrivate
    -0.51
     sorts
    -0.51
    Fitment
    -0.50
    glGen
    -0.50
    POSITIVE LOGITS
    principalTable
    0.63
    出版年
    0.60
    ftagPool
    0.55
    enumii
    0.52
     незавершена
    0.50
    sill
    0.48
    SourceChecksum
    0.48
     onCancelled
    0.47
    sey
    0.46
    EndInit
    0.45
    Activations Density 0.173%

    No Known Activations