© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94461
    Prev
    Next
    INDEX
    Explanations

    of course

    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
    SizeF
    -0.64
     and
    -0.50
    mmate
    -0.50
    amaño
    -0.48
    FileDialog
    -0.47
    ebenarnya
    -0.45
    Données
    -0.45
     Enix
    -0.45
     faktisk
    -0.44
    áček
    -0.43
    POSITIVE LOGITS
     @"/
    0.62
     you
    0.62
    MigrationBuilder
    0.60
    uxxxx
    0.60
    multirow
    0.56
    esModule
    0.56
    Билгалдахарш
    0.56
    __*/
    0.56
    kloped
    0.55
    __":
    0.55
    Activations Density 0.002%

    No Known Activations