© 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. 2-RES-MATRYOSHKA-DC
    7. 7069
    Prev
    Next
    INDEX
    Explanations

    references to Pacific Islander and Oceanian ethnic groups

    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
    KommentareTeilen
    -0.78
    photobucket
    -0.61
    мак
    -0.60
    udas
    -0.58
    ScreenState
    -0.57
    printLine
    -0.56
    getRuntime
    -0.54
    OSA
    -0.52
    ăți
    -0.52
     Zorn
    -0.52
    POSITIVE LOGITS
     Pacific
    3.66
    Pacific
    3.42
     PACIFIC
    3.25
     pacific
    2.94
    pacific
    2.73
     Pacífico
    2.34
     Pac
    2.00
    太平洋
    1.95
    Pac
    1.87
     Atlantic
    1.62
    Activations Density 0.008%

    No Known Activations