© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40016
    Prev
    Next
    INDEX
    Explanations

    morbidity

    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
     Anſ
    -0.87
     Diſ
    -0.81
     Theſe
    -0.81
    PreferredItem
    -0.79
     Inſ
    -0.76
     CHAPITRE
    -0.76
     ſeveral
    -0.74
     تضيفلها
    -0.73
    thâu
    -0.73
    DockStyle
    -0.73
    POSITIVE LOGITS
     is
    0.56
    .
    0.52
    a
    0.49
     eventdata
    0.49
     of
    0.48
     (
    0.47
    War
    0.45
    expert
    0.45
     I
    0.45
    i
    0.44
    Activations Density 0.038%

    No Known Activations