© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2852
    Prev
    Next
    INDEX
    Explanations

    location and continuation

    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
    MigrationBuilder
    -0.77
    webElementXpaths
    -0.74
    mybatisplus
    -0.72
     للاسماء
    -0.72
    hoeddwyd
    -0.71
    
    -0.68
    GEBURTSDATUM
    -0.64
    存于互联网档案馆
    -0.64
    IntoConstraints
    -0.62
     nahilalakip
    -0.59
    POSITIVE LOGITS
     up
    0.64
    ाहरण
    0.51
     several
    0.50
     five
    0.47
     organizing
    0.46
     four
    0.46
    Hướng
    0.46
     lên
    0.45
     throughout
    0.45
     enca
    0.45
    Activations Density 0.006%

    No Known Activations