© 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. 1-RES-MATRYOSHKA-DC
    7. 659
    Prev
    Next
    INDEX
    Explanations

    references to academic or research organizations

    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
     Portuguese
    -0.81
     Spanish
    -0.79
     Greek
    -0.77
     French
    -0.75
     Chinese
    -0.73
    Spanish
    -0.72
     Italian
    -0.71
    Portuguese
    -0.70
     German
    -0.69
     Japanese
    -0.69
    POSITIVE LOGITS
     American
    3.63
    American
    3.56
     AMERICAN
    3.33
     american
    3.14
    AMERICAN
    3.08
    american
    3.00
     America
    2.83
     Americans
    2.80
    America
    2.59
    Americans
    2.58
    Activations Density 0.263%

    No Known Activations