© 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. 3-RES-MATRYOSHKA-DC
    7. 1022
    Prev
    Next
    INDEX
    Explanations

    words that relate to specific regions, nationalities or languages, especially Chinese and Italian

    oai_token-act-pair · gemini-2.0-flash
    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
     kasarigan
    -0.89
    tvguidetime
    -0.75
    énario
    -0.69
    calientes
    -0.66
     USA
    -0.66
     EEUU
    -0.64
     States
    -0.63
    caux
    -0.61
    ghalaya
    -0.58
     states
    -0.56
    POSITIVE LOGITS
     Italian
    1.55
     Japanese
    1.49
    Italian
    1.44
     Chinese
    1.41
    Japanese
    1.41
     Mexican
    1.36
     Vietnamese
    1.35
     Indian
    1.32
     Russian
    1.31
     French
    1.30
    Activations Density 1.110%

    No Known Activations