© 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. 44220
    Prev
    Next
    INDEX
    Explanations

    ears

    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
     ears
    -2.25
     Ears
    -1.63
     oreilles
    -1.04
     oídos
    -0.93
     orejas
    -0.92
    耳朵
    -0.87
    ears
    -0.79
     CreateTagHelper
    -0.76
     оригіналу
    -0.73
     referenties
    -0.72
    POSITIVE LOGITS
    Bonjour
    0.51
    bonjour
    0.47
    hip
    0.45
    pinas
    0.45
     مُعرِّف
    0.43
     coper
    0.43
     aria
    0.42
    pædia
    0.42
    ària
    0.42
     חיצוניים
    0.42
    Activations Density 0.185%

    No Known Activations