© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 95035
    Prev
    Next
    INDEX
    Explanations

    util

    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
    ah
    -0.82
    rim
    -0.60
    WithIOException
    -0.51
    are
    -0.50
    a
    -0.49
    prepareStatement
    -0.48
     cercano
    -0.48
    USH
    -0.47
    ait
    -0.47
    aye
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.73
     itſelf
    0.68
    ."],
    0.68
    utives
    0.66
    /*---
    0.65
    phans
    0.65
     azy
    0.64
    MessageTagHelper
    0.63
    fully
    0.63
     lept
    0.63
    Activations Density 0.060%

    No Known Activations