© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11849
    Prev
    Next
    INDEX
    Explanations

    references to Denmark and its related entities

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    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
    ande
    -0.86
     Yale
    -0.73
    PreExecute
    -0.71
    awtextra
    -0.67
    modelBuilder
    -0.65
    Yale
    -0.64
    륙
    -0.60
    ंदीखरीदारी
    -0.58
    HomeAsUpEnabled
    -0.57
     مشين
    -0.56
    POSITIVE LOGITS
     Danish
    1.52
     Denmark
    1.45
    Danish
    1.30
     Copenhagen
    1.23
     Danes
    1.20
    Denmark
    1.09
     danish
    1.09
     Dane
    0.95
     Dinamarca
    0.79
     Danmark
    0.78
    Activations Density 0.019%

    No Known Activations