© 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. 0-CLT-HP
    7. 43292
    Prev
    Next
    INDEX
    Explanations

    deals, organization, cleaning

    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
     Jefus
    -1.21
     Majefty
    -1.19
     Efq
    -1.16
     Monfieur
    -1.14
     raiſ
    -1.11
     pleaſure
    -1.09
     Reſ
    -1.09
     nahilalakip
    -1.07
     itſelf
    -1.07
     Houſe
    -1.06
    POSITIVE LOGITS
     "
    0.63
    щи
    0.57
     
    0.57
    <eos>
    0.56
     For
    0.56
     H
    0.54
     “
    0.54
     In
    0.50
    ighted
    0.49
    igen
    0.49
    Activations Density 0.090%

    No Known Activations