Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4149
    Prev
    Next
    INDEX
    Explanations

    Legal/scientific documents

    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
    <eos>
    -0.50
     or
    -0.50
    -
    -0.49
     
    -0.48
    ↵↵
    -0.46
     "
    -0.46
    ’
    -0.45
    '
    -0.45
    ro
    -0.44
     &
    -0.43
    POSITIVE LOGITS
     Normdatei
    0.91
     myſelf
    0.83
     Efq
    0.80
     Jefus
    0.78
     '\\;'
    0.76
     Majefty
    0.75
    mặt
    0.75
     للاسماء
    0.74
    eseorang
    0.73
     Shakspeare
    0.73
    Activations Density 0.002%

    No Known Activations