© 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. 2-RES-MATRYOSHKA-DC
    7. 5016
    Prev
    Next
    INDEX
    Explanations

    references or mentions of the term "British."

    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
     IRELAND
    -0.65
     Welsh
    -0.64
    Welsh
    -0.60
     Irlanda
    -0.58
     ireland
    -0.57
    pshire
    -0.56
    lawesi
    -0.56
     Ireland
    -0.56
     continúas
    -0.56
    Ireland
    -0.55
    POSITIVE LOGITS
     British
    2.19
    British
    2.17
     BRITISH
    1.95
     british
    1.80
    british
    1.71
    BRIT
    1.47
     Britain
    1.30
    Britain
    1.30
     Brit
    1.20
     Brits
    1.20
    Activations Density 0.007%

    No Known Activations