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. 14042
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement, especially police

    oai_token-act-pair · gemini-2.0-flash

    police

    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
     CreateTagHelper
    -0.89
    脚注の使い方
    -0.85
    ConstraintMaker
    -0.84
    AddTagHelper
    -0.75
    ImageContext
    -0.75
    出版年
    -0.73
    adpleegd
    -0.71
     EconPapers
    -0.69
    CloseOperation
    -0.65
     gynhyrchwyd
    -0.64
    POSITIVE LOGITS
    نجليز
    0.49
    ͡
    0.45
     officers
    0.44
     commissioner
    0.44
    man
    0.43
     Scip
    0.43
    +#+#
    0.43
    äden
    0.42
    mens
    0.42
    vertx
    0.41
    Activations Density 0.969%

    No Known Activations