© 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. 0-RES-MATRYOSHKA-DC
    7. 10992
    Prev
    Next
    INDEX
    Explanations

    a comparison or similarity between different datasets, models, or methods

    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
     contrast
    -1.10
    contrast
    -1.09
     Contrast
    -0.85
    Contrast
    -0.83
     contrasts
    -0.82
    JsonInclude
    -0.77
     contraste
    -0.75
     contrasted
    -0.73
    databind
    -0.71
    AnimationsModule
    -0.70
    POSITIVE LOGITS
    Comparison
    2.08
     Comparison
    1.35
     COMPARISON
    0.70
    Relationship
    0.62
     Relationship
    0.59
     RELATIONSHIP
    0.57
    RegistryLite
    0.54
     باخ
    0.54
    Viitteet
    0.54
     années
    0.53
    Activations Density 0.002%

    No Known Activations