© 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. 12-RES-MATRYOSHKA-DC
    7. 10520
    Prev
    Next
    INDEX
    Explanations

    terms related to pairwise comparisons or interactions in statistical analyses

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     Pemberton
    -0.75
     Spector
    -0.74
     Schmel
    -0.73
     kasarigan
    -0.72
    SupportActionBar
    -0.72
     bezeichneter
    -0.72
    unmodifiable
    -0.72
     Colonna
    -0.71
     McDonough
    -0.71
    ctuation
    -0.70
    POSITIVE LOGITS
    wise
    1.21
    WISE
    1.10
    Wise
    0.94
    ly
    0.91
     WISE
    0.88
     Wise
    0.86
     Wiseman
    0.85
     wise
    0.82
     pairwise
    0.69
     bross
    0.69
    Activations Density 0.007%

    No Known Activations