Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16275
    Prev
    Next
    INDEX
    Explanations

    terms related to online chat and flight simulations

    oai_token-act-pair · gemini-2.0-flash

    chat

    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
    ArrowToggle
    -0.90
    SourceChecksum
    -0.76
     BoxFit
    -0.73
    oneofs
    -0.72
     propOrder
    -0.71
    tagHelper
    -0.69
    ViewFeatures
    -0.68
     ModelExpression
    -0.67
    SpringRunner
    -0.67
    principalTable
    -0.67
    POSITIVE LOGITS
     publiques
    0.49
     plane
    0.43
    öhe
    0.42
    Plane
    0.41
     humain
    0.41
     trânsito
    0.40
     onResponse
    0.40
     industriales
    0.40
     sal
    0.38
    plane
    0.38
    Activations Density 6.646%

    No Known Activations