© 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. 1-CLT-HP
    7. 15468
    Prev
    Next
    INDEX
    Explanations

    ladies

    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
     NDL
    -0.60
    KommentareTeilen
    -0.59
    PRWEB
    -0.45
     passed
    -0.44
    SaveChangesAsync
    -0.44
    oneph
    -0.43
    putan
    -0.43
    trends
    -0.42
    jemah
    -0.41
     savez
    -0.41
    POSITIVE LOGITS
    <bos>
    1.07
    хьтан
    0.70
     виправивши
    0.67
     ddelweddau
    0.65
     disambiguazione
    0.60
    //
    0.59
    市镇
    0.58
    السكان
    0.56
     rêver
    0.56
     Crawford
    0.55
    Activations Density 0.006%

    No Known Activations