© 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. 20-CLT-HP
    7. 74725
    Prev
    Next
    INDEX
    Explanations

    technical texts

    np_max-act-logits · 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
     kasarigan
    -0.66
     AssemblyTitle
    -0.63
    UrlResolution
    -0.61
     createContext
    -0.60
     ویکی‌پدیای
    -0.58
    úgó
    -0.56
    ều
    -0.54
     UIKit
    -0.53
     considérons
    -0.53
    Personensuche
    -0.53
    POSITIVE LOGITS
     odes
    0.46
    toMatchSnapshot
    0.43
    lwjgl
    0.42
    которые
    0.40
     Krieger
    0.39
     yoksa
    0.38
    krom
    0.38
    transQ
    0.37
     Heiden
    0.37
    Few
    0.36
    Activations Density 0.000%

    No Known Activations