© 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. 45292
    Prev
    Next
    INDEX
    Explanations

    observations

    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
    -0.80
    WebElementEntity
    -0.75
    bewerken
    -0.73
    بوابة
    -0.66
    Demografie
    -0.66
    awaiter
    -0.63
    kloped
    -0.62
    urbation
    -0.62
     nakalista
    -0.62
    fiore
    -0.61
    POSITIVE LOGITS
     espagne
    0.70
    AndroidJUnit
    0.65
    ⓧ
    0.56
     päivä
    0.54
     inoxidable
    0.54
     africaine
    0.54
    addContainerGap
    0.53
     roulant
    0.52
     inoxydable
    0.51
     cérami
    0.50
    Activations Density 0.409%

    No Known Activations