© 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. 4-CLT-HP
    7. 56
    Prev
    Next
    INDEX
    Explanations

    and

    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
    +#+#
    -0.76
    はじめに
    -0.73
    Дереккөздер
    -0.70
    Personensuche
    -0.66
    Hochspringen
    -0.63
     الاطلاع
    -0.60
    WriteTagHelper
    -0.60
    Aholisi
    -0.56
    Šaltiniai
    -0.54
    Lähteet
    -0.54
    POSITIVE LOGITS
    ocellular
    0.50
     clicar
    0.50
     caloric
    0.49
    '&:
    0.49
    owulf
    0.48
     Serap
    0.48
    autoreleasepool
    0.47
     crat
    0.47
    TRUNC
    0.47
     škole
    0.47
    Activations Density 0.008%

    No Known Activations