© 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. 4-CLT-HP
    7. 3486
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
     ExecuteAsync
    -0.50
    nyata
    -0.49
     then
    -0.46
     your
    -0.46
    때
    -0.45
    getRaw
    -0.43
    aires
    -0.43
     StatelessWidget
    -0.43
    TextBoxColumn
    -0.42
    HasIndex
    -0.42
    POSITIVE LOGITS
     will
    1.11
     may
    0.76
     can
    0.73
    ftagPool
    0.73
     WILL
    0.71
     الرياضيه
    0.71
    will
    0.70
     akan
    0.68
    abestanden
    0.66
    SequentialGroup
    0.66
    Activations Density 0.011%

    No Known Activations