© 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. 0-CLT-HP
    7. 39004
    Prev
    Next
    INDEX
    Explanations

    called

    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
     called
    -0.61
    called
    -0.56
    Called
    -0.43
     héri
    -0.43
     chamada
    -0.42
     llamada
    -0.41
     называется
    -0.41
     kasar
    -0.40
    évaluateur
    -0.40
     passent
    -0.40
    POSITIVE LOGITS
    __*/
    1.09
    BeginInit
    1.02
    ].)
    0.78
     <",
    0.71
    ChildScrollView
    0.71
    ]").
    0.71
     calldata
    0.69
    AddHtmlAttribute
    0.68
    interopRequire
    0.68
     unknownFields
    0.68
    Activations Density 0.696%

    No Known Activations