Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74217
    Prev
    Next
    INDEX
    Explanations

    the

    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
    parsedMessage
    -0.82
    IntoConstraints
    -0.80
    ValueStyle
    -0.77
    WithIOException
    -0.75
     GoogleFonts
    -0.75
     ſind
    -0.73
    RegressionTest
    -0.72
    InputBorder
    -0.71
     AssemblyCompany
    -0.69
     autorytatywna
    -0.69
    POSITIVE LOGITS
     hook
    0.34
     sunroof
    0.33
    No
    0.32
     lengkap
    0.30
    ELINE
    0.30
    #{
    0.30
    みな
    0.29
    HOOK
    0.29
     teritor
    0.29
     ver
    0.28
    Activations Density 0.747%

    No Known Activations