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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91024
    Prev
    Next
    INDEX
    Explanations

    Computer graphics

    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
    MigrationBuilder
    -1.25
    IsMutable
    -1.07
     referenties
    -1.05
     kittens
    -1.05
    DeleteBehavior
    -1.05
     myſelf
    -1.05
     Roskov
    -1.04
    extAlignment
    -1.02
     insects
    -1.00
     disambiguazione
    -1.00
    POSITIVE LOGITS
    ,
    0.84
    .
    0.84
     (
    0.76
     
    0.72
     and
    0.68
     in
    0.65
     the
    0.65
     that
    0.63
    line
    0.60
    men
    0.59
    Activations Density 0.281%

    No Known Activations