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. 74327
    Prev
    Next
    INDEX
    Explanations

    health and healthcare

    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
    ValueStyle
    -0.90
    xampp
    -0.67
    بوابة
    -0.63
    ImageContext
    -0.63
    MessageTagHelper
    -0.62
    LabelTagHelper
    -0.62
     تضيفلها
    -0.62
    StoryboardSegue
    -0.62
     ")");
    -0.59
    fjspx
    -0.59
    POSITIVE LOGITS
     فريبيس
    0.61
    SequentialGroup
    0.53
    RunAsync
    0.43
    ğraf
    0.43
     Stil
    0.42
     reven
    0.42
     BoxFit
    0.42
    Sn
    0.41
     EDU
    0.41
     Bix
    0.40
    Activations Density 0.001%

    No Known Activations