© 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. 45196
    Prev
    Next
    INDEX
    Explanations

    light

    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
     light
    -1.73
     Light
    -1.14
    Light
    -1.04
    light
    -0.96
     LIGHT
    -0.94
     lighter
    -0.91
     licht
    -0.82
     léger
    -0.77
    LIGHT
    -0.75
     leichten
    -0.73
    POSITIVE LOGITS
    PreferredItem
    0.75
    boats
    0.73
    تقاوى
    0.70
    guns
    0.68
    bombs
    0.64
    wires
    0.62
    contentLoaded
    0.62
    trains
    0.60
    ings
    0.60
    bars
    0.60
    Activations Density 0.043%

    No Known Activations