© 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. 4-CLT-HP
    7. 3501
    Prev
    Next
    INDEX
    Explanations

    Numbers and codes

    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
    HasForeignKey
    -0.55
    Gambas
    -0.52
    ftagPool
    -0.47
     وتسجيلات
    -0.47
    BeginContext
    -0.44
    まず
    -0.44
    ########.
    -0.43
     typelib
    -0.42
    やら
    -0.40
    ɕ
    -0.40
    POSITIVE LOGITS
    :✨
    0.66
     AspNetCore
    0.66
    ŚĆ
    0.65
     formulae
    0.64
     createTime
    0.63
    viembre
    0.62
    trav
    0.62
    skraft
    0.60
     Voltaire
    0.60
    quillas
    0.60
    Activations Density 0.241%

    No Known Activations