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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1674
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the military, particularly the US Marine Corps

    oai_token-act-pair · gemini-2.0-flash

    military/government operations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     ostavi
    -0.68
    :✨
    -0.68
    دانشنامهٔ
    -0.63
     nahilalakip
    -0.63
     doInBackground
    -0.62
    الحياه
    -0.61
     AspNetCore
    -0.59
    LookAnd
    -0.56
    @[+][
    -0.56
     незавершена
    -0.55
    POSITIVE LOGITS
     authorities
    0.73
     Authorities
    0.72
    Authorities
    0.62
    authorities
    0.57
    ípio
    0.56
    XmlAccessType
    0.53
    carded
    0.49
    onShow
    0.49
    borgs
    0.48
     police
    0.48
    Activations Density 12.677%

    No Known Activations