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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15511
    Prev
    Next
    INDEX
    Explanations

    references to specific country names and sports teams

    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
    AsUp
    -0.84
     ISNI
    -0.81
     Dalai
    -0.79
    Personensuche
    -0.76
     EconPapers
    -0.75
    RenderAtEndOf
    -0.74
    GraphicsUnit
    -0.74
    Abitanti
    -0.73
    ⓧ
    -0.72
    enumi
    -0.72
    POSITIVE LOGITS
     Romania
    2.20
     Romanian
    1.90
     Bulgaria
    1.80
    Romania
    1.77
     Bulgarian
    1.47
     Bucharest
    1.42
     Roumanie
    1.35
    Bulgaria
    1.28
    Bulg
    1.17
     Rumania
    1.12
    Activations Density 0.001%

    No Known Activations