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. 14175
    Prev
    Next
    INDEX
    Explanations

    negative imperatives containing "miss" or "feel"

    oai_token-act-pair · 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
     lontano
    -0.45
     either
    -0.42
    Hash
    -0.41
    oflavin
    -0.40
    cadilly
    -0.39
     innoc
    -0.39
     never
    -0.38
     impunity
    -0.38
    itus
    -0.38
     harmless
    -0.37
    POSITIVE LOGITS
    ValueStyle
    0.99
    IsMutable
    0.84
    MigrationBuilder
    0.84
    AddTagHelper
    0.82
    ChildScrollView
    0.78
    ConstraintMaker
    0.76
    migrationBuilder
    0.75
    protoimpl
    0.73
     combineReducers
    0.72
    StructEnd
    0.71
    Activations Density 0.437%

    No Known Activations