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. 22-CLT-HP
    4. 74606
    Prev
    Next
    INDEX
    Explanations

    re- prefix

    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
    IndentedString
    -0.86
     समीक्षाओं
    -0.80
     Baillargeon
    -0.78
     الرياضيه
    -0.75
     nahilalakip
    -0.74
    AntiForgeryToken
    -0.74
     annealed
    -0.67
     >=",
    -0.67
     itſelf
    -0.65
     loob
    -0.65
    POSITIVE LOGITS
     pop
    0.64
    pop
    0.48
    dist
    0.47
    iss
    0.45
    valid
    0.45
    med
    0.45
     lähe
    0.44
    Valid
    0.43
     Pop
    0.43
    ty
    0.42
    Activations Density 0.001%

    No Known Activations