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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74000
    Prev
    Next
    INDEX
    Explanations

    code, database queries

    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
     '\\;'
    -0.70
     كومونز
    -0.68
    moveToFirst
    -0.67
    Diweddarwch
    -0.66
    writeFieldEnd
    -0.63
     ProtoMessage
    -0.63
    BufferException
    -0.61
    expandindo
    -0.61
     صوتيه
    -0.61
    SharedCtor
    -0.60
    POSITIVE LOGITS
    True
    0.50
    resz
    0.46
    pageTitle
    0.45
     hű
    0.43
    true
    0.43
    atista
    0.43
     albero
    0.41
     Pingback
    0.41
     True
    0.41
     true
    0.41
    Activations Density 0.000%

    No Known Activations