© 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. 1065
    Prev
    Next
    INDEX
    Explanations

    references to major matrix types or properties

    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
    ếng
    -0.45
    isen
    -0.44
    テン
    -0.43
    uteria
    -0.43
     물
    -0.42
     mert
    -0.42
    низ
    -0.42
    elsen
    -0.42
    足够
    -0.40
     Del
    -0.40
    POSITIVE LOGITS
     major
    4.47
    major
    4.47
    Major
    4.25
     Major
    4.00
     MAJOR
    3.92
    MAJOR
    3.86
     majors
    2.94
     minor
    2.70
    minor
    2.70
    Minor
    2.61
    Activations Density 0.042%

    No Known Activations