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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16200
    Prev
    Next
    INDEX
    Explanations

    mentions of sentencing within legal contexts

    oai_token-act-pair · gemini-2.0-flash

    technical jargon

    np_token-act-pair-logits · gemini-2.0-flash

    court sentences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     quæ
    -0.56
    енча
    -0.53
    rrggbb
    -0.50
     ErrInvalid
    -0.48
     peine
    -0.48
     peines
    -0.47
    Demikian
    -0.47
     NUKAT
    -0.44
    universe
    -0.44
    :✨
    -0.43
    POSITIVE LOGITS
    kháu
    0.60
    UserScript
    0.59
    RotationOrder
    0.55
    HasColumnType
    0.54
    csrf
    0.52
    olino
    0.52
    NOPQRST
    0.51
    InteropServices
    0.51
    isRequired
    0.51
    外部リンク
    0.50
    Activations Density 3.425%

    No Known Activations