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. 0-CLT-HP
    4. 44416
    Prev
    Next
    INDEX
    Explanations

    Former

    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
     former
    -1.43
    Former
    -1.24
    former
    -1.23
     Former
    -1.13
    fields
    -0.89
     formerly
    -0.83
    lands
    -0.83
     fields
    -0.79
     mantan
    -0.73
     ehemaligen
    -0.71
    POSITIVE LOGITS
    mybatisplus
    0.97
    
    0.90
    ImageContext
    0.88
    BeginContext
    0.88
     endblock
    0.87
    ValueStyle
    0.85
    出版年
    0.85
    AddHtmlAttribute
    0.82
    \{\\
    0.82
     ویکی‌پدیا
    0.82
    Activations Density 1.813%

    No Known Activations