© 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. 413
    Prev
    Next
    INDEX
    Explanations

    references to small size or scale

    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
    BIG
    -0.80
    Big
    -0.80
     Big
    -0.79
    big
    -0.77
     big
    -0.72
     BIG
    -0.72
     ModelExpression
    -0.68
    bigg
    -0.68
    enumi
    -0.63
     majeurs
    -0.63
    POSITIVE LOGITS
     small
    3.70
    small
    3.48
    Small
    3.41
     Small
    3.31
     SMALL
    3.19
    SMALL
    2.97
     smaller
    2.66
     tiny
    2.63
     pequeños
    2.53
     smallest
    2.48
    Activations Density 1.474%

    No Known Activations