© 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. 5-CLT-HP
    7. 999
    Prev
    Next
    INDEX
    Explanations

    :

    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
    VersionUID
    -0.56
    styleUrls
    -0.54
     gra
    -0.52
     XCTest
    -0.52
    FetchType
    -0.52
     Brig
    -0.52
     Anz
    -0.49
    Errorf
    -0.49
    romas
    -0.49
    ridor
    -0.48
    POSITIVE LOGITS
     stället
    0.65
     فريبيس
    0.63
    WebElementEntity
    0.62
     Normdatei
    0.60
    izarse
    0.57
    éndolo
    0.57
     quæ
    0.57
     vägen
    0.56
    Попис
    0.56
    Beijinhos
    0.55
    Activations Density 0.000%

    No Known Activations