© 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. 20-CLT-HP
    7. 71757
    Prev
    Next
    INDEX
    Explanations

    code/technical texts

    np_max-act-logits · 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
    HideFlags
    -0.69
    hicule
    -0.66
    UrlResolution
    -0.66
    protoimpl
    -0.63
    UnusedPrivate
    -0.62
     ویکی‌پدیای
    -0.60
     Мексичка
    -0.59
    Segoe
    -0.56
    PAIGN
    -0.55
    bootstrapcdn
    -0.55
    POSITIVE LOGITS
    rsc
    0.58
     black
    0.50
    ason
    0.50
     Mead
    0.47
     BLACK
    0.46
     Rump
    0.45
    ainen
    0.45
     Black
    0.44
    black
    0.44
     useDispatch
    0.43
    Activations Density 0.006%

    No Known Activations