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. 14153
    Prev
    Next
    INDEX
    Explanations

    legal jargon related to sentencing and probation

    oai_token-act-pair · gemini-2.0-flash

    legal sentencing

    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
     виправивши
    -0.75
     protoimpl
    -0.60
     StatelessWidget
    -0.59
    UnknownFieldSet
    -0.59
     FetchType
    -0.54
    migrationBuilder
    -0.50
    siella
    -0.50
     intim
    -0.48
    NameInMap
    -0.44
     terciopelo
    -0.44
    POSITIVE LOGITS
     ſte
    0.59
    loài
    0.56
     EconPapers
    0.56
    PullParser
    0.56
     发表于
    0.54
     supervised
    0.53
    xffffff
    0.53
    conceito
    0.52
    reportWebVitals
    0.52
    ForRow
    0.52
    Activations Density 2.129%

    No Known Activations