© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1533
    Prev
    Next
    INDEX
    Explanations

    references to scientific analyses or statistical evaluations

    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
    Negative Logits
     expéri
    -0.90
     test
    -0.79
     experimentally
    -0.79
     EXPERIMENTAL
    -0.76
     Experimental
    -0.75
     experimental
    -0.75
    Experimental
    -0.74
     TEST
    -0.73
     expériment
    -0.73
    Test
    -0.71
    POSITIVE LOGITS
     analysis
    3.75
     Analysis
    3.61
    analysis
    3.47
    Analysis
    3.44
     ANALYSIS
    3.33
     analyses
    3.00
    ANALYSIS
    2.91
     Analyses
    2.83
    analyses
    2.67
     análisis
    2.64
    Activations Density 0.180%

    No Known Activations