© 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. 5-CLT-HP
    7. 2118
    Prev
    Next
    INDEX
    Explanations

    years

    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
    .
    -0.62
    -
    -0.49
    ↵
    -0.47
    ko
    -0.47
     –
    -0.46
    J
    -0.46
    eventbus
    -0.46
    xp
    -0.45
    ok
    -0.44
    OK
    -0.44
    POSITIVE LOGITS
    EndGlobalSection
    0.85
     purpoſe
    0.82
     Efq
    0.77
     faſt
    0.73
    ...');
    0.72
    ();)
    0.72
    ^(@)
    0.71
     itſelf
    0.71
    NUMX
    0.71
    notag
    0.70
    Activations Density 0.031%

    No Known Activations