© 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. 14491
    Prev
    Next
    INDEX
    Explanations

    glioma

    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
    enumi
    -0.73
    windowFixed
    -0.71
     دیکھیے
    -0.64
    Jereo
    -0.63
     Ababa
    -0.62
    undam
    -0.60
    Personendaten
    -0.60
    ArgsConstructor
    -0.59
     незавершена
    -0.59
     gneiss
    -0.58
    POSITIVE LOGITS
    mögen
    0.45
    nvarchar
    0.45
     sub
    0.45
    flügel
    0.44
    udu
    0.42
     λειτουργ
    0.41
     futility
    0.41
    య
    0.41
    ειτουργ
    0.40
    reiben
    0.40
    Activations Density 0.012%

    No Known Activations