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. 74559
    Prev
    Next
    INDEX
    Explanations

    the

    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
     NSCoder
    -0.75
     EconPapers
    -0.72
    yntaxException
    -0.63
    ьаж
    -0.62
    rrggbb
    -0.57
    "](
    -0.56
    ;=
    -0.55
    gameserver
    -0.54
    BufferException
    -0.54
    "}")
    -0.54
    POSITIVE LOGITS
    WritableDatabase
    0.50
     Fasc
    0.42
     tuyo
    0.41
    complish
    0.41
    rsa
    0.40
     Ele
    0.40
    Portale
    0.40
     florales
    0.39
    RectangleBorder
    0.39
     bunga
    0.39
    Activations Density 0.043%

    No Known Activations