© 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. 45305
    Prev
    Next
    INDEX
    Explanations

    social issues and identity

    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
     pinulongan
    -0.75
    +#+#
    -0.71
    WEBPACK
    -0.70
    AddTagHelper
    -0.70
    InjectAttribute
    -0.67
    //
    -0.66
    Välislingid
    -0.66
    ListItemIcon
    -0.66
    RuleContext
    -0.63
    katapos
    -0.63
    POSITIVE LOGITS
    ism
    0.83
    er
    0.81
    ized
    0.75
    ed
    0.74
    ization
    0.73
    ity
    0.71
    ised
    0.68
    isms
    0.68
    eries
    0.67
     Theſe
    0.65
    Activations Density 1.592%

    No Known Activations