© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12439
    Prev
    Next
    INDEX
    Explanations

    references to specific geographies and territorial regions

    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
    DockStyle
    -1.00
    AnchorStyles
    -0.71
     JpaRepository
    -0.68
     màn
    -0.67
    abestanden
    -0.67
    expandindo
    -0.67
    BlockingQueue
    -0.66
    MemoryWarning
    -0.66
    ukunft
    -0.65
     للاسماء
    -0.65
    POSITIVE LOGITS
    sten
    1.36
    tomic
    1.32
    uff
    0.95
    STEN
    0.87
    lioma
    0.83
    stens
    0.70
    时
    0.57
    時的
    0.51
    时的
    0.47
    reportError
    0.47
    Activations Density 0.003%

    No Known Activations