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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6000
    Prev
    Next
    INDEX
    Explanations

    references to international politics and economics, particularly with Russia, China, and the United States

    oai_token-act-pair · gemini-2.0-flash

    names of countries or concepts related to geopolitics

    np_token-act-pair-logits · gpt-4o-mini

    International relations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    搏
    -0.52
     recommandons
    -0.50
    gim
    -0.47
    DataObject
    -0.45
    amit
    -0.45
    wani
    -0.45
     desafi
    -0.45
    ]]=
    -0.45
    zna
    -0.44
     bañ
    -0.43
    POSITIVE LOGITS
     Turkey
    0.75
     America
    0.75
    StoryboardSegue
    0.73
     foreigners
    0.71
     Mauritania
    0.69
     Iraq
    0.69
    帖最后由
    0.68
     democracy
    0.68
    OGND
    0.68
     ſmall
    0.67
    Activations Density 10.745%

    No Known Activations