© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10913
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous text snippets

    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
    extAlignment
    -0.69
     مشارکت‌کنندگان
    -0.66
     mourut
    -0.65
     commerciaux
    -0.64
     tué
    -0.63
    toad
    -0.63
     giustizia
    -0.63
     fausse
    -0.63
     africains
    -0.61
     chaude
    -0.60
    POSITIVE LOGITS
     فريبيس
    0.55
     <<<<<<<<<<<<<<
    0.50
    Abitanti
    0.46
     ***!
    0.45
    >({
    0.44
    eba
    0.43
    InjectAttribute
    0.42
    elemField
    0.42
     paro
    0.41
     }}"></
    0.41
    Activations Density 0.024%

    No Known Activations