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. 74616
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    AsUp
    -0.73
    complexContent
    -0.71
    transQ
    -0.65
    //
    -0.60
    RegressionTest
    -0.59
    /**
    -0.57
    oredCriteria
    -0.56
    TestFixture
    -0.56
    UrlResolution
    -0.54
    PerformLayout
    -0.54
    POSITIVE LOGITS
    onyx
    0.56
    InputBorder
    0.48
    ····
    0.48
     تضيفلها
    0.47
    actos
    0.47
    "><?=
    0.47
     RSSSF
    0.45
    DebuggerNonUser
    0.44
    γεν
    0.44
     اطلع
    0.44
    Activations Density 0.012%

    No Known Activations