© 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. 91100
    Prev
    Next
    INDEX
    Explanations

    disturb

    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
    able
    -0.92
     disturbance
    -0.90
     disturbed
    -0.90
     disturbances
    -0.84
     disturb
    -0.77
    urbed
    -0.75
     Disturb
    -0.74
    timately
    -0.73
    IntoConstraints
    -0.71
     onOptions
    -0.68
    POSITIVE LOGITS
    s
    0.59
    t
    0.56
    mas
    0.53
    le
    0.53
    tra
    0.52
    rel
    0.50
    scale
    0.50
    mo
    0.50
    nic
    0.50
    sm
    0.49
    Activations Density 0.085%

    No Known Activations