© 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. 6612
    Prev
    Next
    INDEX
    Explanations

    references to Australian entities, places, or topics related to Australia

    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
     Burnham
    -0.74
     Berks
    -0.70
     Pyle
    -0.65
     Tiber
    -0.63
     angiel
    -0.59
     Lenox
    -0.58
     brancas
    -0.57
    ModelSerializer
    -0.56
     Spire
    -0.56
     Adams
    -0.55
    POSITIVE LOGITS
     Australian
    2.95
     Australia
    2.88
    Australian
    2.67
    Australia
    2.61
     Australians
    2.50
     AUSTRALIA
    2.42
     Aussie
    2.39
     australian
    2.33
     Australien
    2.31
     australia
    2.22
    Activations Density 0.053%

    No Known Activations