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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12844
    Prev
    Next
    INDEX
    Explanations

    immunity

    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
     immunity
    -0.82
     Immunity
    -0.56
    immunity
    -0.54
    amous
    -0.47
    免疫
    -0.44
    munity
    -0.44
    tagHelper
    -0.43
    phal
    -0.42
    ÉD
    -0.41
     freedom
    -0.40
    POSITIVE LOGITS
     виправивши
    0.91
     betweenstory
    0.84
     تضيفلها
    0.80
     itſelf
    0.79
    IntoConstraints
    0.75
     typelib
    0.73
     contextLoads
    0.72
    parsedMessage
    0.71
     myſelf
    0.71
    WriteTagHelper
    0.70
    Activations Density 0.058%

    No Known Activations