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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73814
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
     spoilers
    -0.56
    Parcelize
    -0.52
     sqlSession
    -0.50
     Himo
    -0.49
    JComboBox
    -0.49
     Kef
    -0.48
    slidesToShow
    -0.48
     fleas
    -0.47
    født
    -0.47
    εβ
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.68
    tagHelperRunner
    0.62
    WebElementEntity
    0.60
     EconPapers
    0.58
    RTLD
    0.57
    acchar
    0.53
     Reised
    0.53
    iNdEx
    0.52
    RegressionTest
    0.52
     gynhyrchwyd
    0.52
    Activations Density 0.027%

    No Known Activations