© 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. 90980
    Prev
    Next
    INDEX
    Explanations

    Describing a person

    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
    ATIC
    -0.51
     the
    -0.51
    ADORA
    -0.50
    ATIVA
    -0.49
     cien
    -0.48
     such
    -0.46
    ULATED
    -0.46
    IALES
    -0.45
    :✨
    -0.44
     containing
    -0.44
    POSITIVE LOGITS
    RegressionTest
    0.93
     незавершена
    0.85
    fromnode
    0.80
    ViewImports
    0.80
     فريبيس
    0.78
     Normdatei
    0.78
    Tikang
    0.73
    webElementXpaths
    0.72
    TypedDataSet
    0.72
    RegistryLite
    0.68
    Activations Density 0.462%

    No Known Activations