© 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. 1-CLT-HP
    7. 12261
    Prev
    Next
    INDEX
    Explanations

    royal titles

    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
     Comun
    -0.56
     privada
    -0.50
     personali
    -0.49
     truth
    -0.47
    StrictEqual
    -0.47
    égalité
    -0.46
     disclosure
    -0.46
    caption
    -0.46
     Batalla
    -0.45
     personage
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.87
     BoxFit
    0.76
    thâu
    0.75
     صوتيه
    0.72
    httphttps
    0.70
     ویکی‌پدیای
    0.66
     /\.(
    0.64
    SharedDtor
    0.64
     Waray
    0.63
    twimg
    0.63
    Activations Density 0.005%

    No Known Activations