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. 20-CLT-HP
    4. 74394
    Prev
    Next
    INDEX
    Explanations

    be

    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
    Autoritní
    -1.07
    Datuak
    -0.98
    mybatisplus
    -0.91
     onOptions
    -0.90
     autorytatywna
    -0.89
    >--}}
    -0.88
    出版年
    -0.88
     InputDecoration
    -0.88
    EndInit
    -0.87
    TagHelper
    -0.85
    POSITIVE LOGITS
     in
    0.65
     of
    0.56
     a
    0.47
    get
    0.47
     the
    0.46
    In
    0.42
    in
    0.41
    for
    0.41
    th
    0.39
     to
    0.39
    Activations Density 0.001%

    No Known Activations