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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14037
    Prev
    Next
    INDEX
    Explanations

    legal documents and legal language

    oai_token-act-pair · gemini-2.0-flash

    Philippines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inoxydable
    -0.68
     /\.(
    -0.63
    __':
    
    -0.63
    tanleria
    -0.63
    IUrlHelper
    -0.62
    aarrggbb
    -0.61
     समीक्षक
    -0.60
    Organisateur
    -0.59
    }{*}{
    -0.58
     &_
    -0.58
    POSITIVE LOGITS
    complexContent
    0.78
    のでしょうか
    0.50
    !*\
    0.48
     muualla
    0.47
     Filipino
    0.46
     Mindanao
    0.46
     חיצוניים
    0.46
    addPreferredGap
    0.44
    のだろうか
    0.43
    PA
    0.42
    Activations Density 2.458%

    No Known Activations