© 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. 2-RES-MATRYOSHKA-DC
    7. 2412
    Prev
    Next
    INDEX
    Explanations

    the consistent emphasis on maintaining a specific physical distance or gap

    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
     clearly
    -0.90
    clearly
    -0.79
    Clearly
    -0.79
    +:+
    -0.78
    EndGlobalSection
    -0.76
     Clearly
    -0.74
    Tembelea
    -0.73
     claramente
    -0.72
    خابات
    -0.69
     feminina
    -0.69
    POSITIVE LOGITS
     clearance
    2.55
     Clearance
    2.41
    clearance
    2.28
     cleared
    2.08
     clearances
    2.05
    cleared
    1.95
     clearing
    1.82
    Cleared
    1.78
     Clearing
    1.67
     clears
    1.59
    Activations Density 0.010%

    No Known Activations