© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98156
    Prev
    Next
    INDEX
    Explanations

    Time/Quantity

    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
    IndentedString
    -0.71
    <bos>
    -0.63
     ostavi
    -0.58
     AssemblyCulture
    -0.57
    IsMutable
    -0.56
    AccessorTable
    -0.53
    sizeCache
    -0.51
    SharedDtor
    -0.51
     Infórmanos
    -0.49
    __*/
    -0.48
    POSITIVE LOGITS
     itſelf
    0.72
     незавершена
    0.71
     Jefus
    0.61
     pleaſure
    0.60
     informée
    0.60
    expandindo
    0.57
    inement
    0.56
     himſelf
    0.56
    pertise
    0.55
    enzuela
    0.55
    Activations Density 0.029%

    No Known Activations