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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1611
    Prev
    Next
    INDEX
    Explanations

    words related to legal and conditional language within arguments and judgements

    oai_token-act-pair · gemini-2.0-flash

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    buckle
    -0.52
     StringTokenizer
    -0.51
     Bite
    -0.51
    EndContext
    -0.50
     Beg
    -0.49
    ồn
    -0.48
     rb
    -0.48
    евна
    -0.48
     AB
    -0.47
    ABCD
    -0.47
    POSITIVE LOGITS
    PerformLayout
    0.67
    WebElementEntity
    0.58
    出版年
    0.56
    ConstraintMaker
    0.56
    ).__
    0.55
    cranial
    0.55
    Демографія
    0.54
     Réponses
    0.54
    Билгалдахарш
    0.54
    tanleria
    0.52
    Activations Density 7.864%

    No Known Activations