© 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. 20-CLT-HP
    7. 74722
    Prev
    Next
    INDEX
    Explanations

    Code and descriptions

    np_max-act-logits · 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
     صوتيه
    -0.78
    gameserver
    -0.72
    出版年
    -0.71
     للمعارف
    -0.69
     الرياضيه
    -0.68
    MessageOf
    -0.67
     Мексичка
    -0.65
    PMailer
    -0.62
    RectangleBorder
    -0.61
     Autorizaciones
    -0.59
    POSITIVE LOGITS
     consultato
    0.52
    lue
    0.51
     essentially
    0.50
    uscular
    0.48
    essentially
    0.48
     basically
    0.48
    يمق
    0.47
    Normdaten
    0.46
     ur
    0.46
     šť
    0.46
    Activations Density 0.000%

    No Known Activations