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. 14124
    Prev
    Next
    INDEX
    Explanations

    text about killing insects and other small creatures

    oai_token-act-pair · gemini-2.0-flash

    Species of insects

    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
     jadx
    -0.53
    MemoryWarning
    -0.50
    ngrx
    -0.50
    וויק
    -0.49
    Mediabestanden
    -0.49
    postmedia
    -0.47
    odeon
    -0.45
    basicConfig
    -0.44
    parsedMessage
    -0.43
     gostar
    -0.42
    POSITIVE LOGITS
    ThroughAttribute
    0.66
    */),
    0.60
    }:${
    0.58
    migrationBuilder
    0.57
    flies
    0.57
    Diweddarwch
    0.56
    melten
    0.54
    canestro
    0.54
     flies
    0.54
    히
    0.51
    Activations Density 1.596%

    No Known Activations