© 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. 0-RES-MATRYOSHKA-DC
    7. 10515
    Prev
    Next
    INDEX
    Explanations

    architectural elements related to aisles, corridors, and structural divisions within buildings, especially in religious or historic structures

    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
    
    -0.56
     Eberhard
    -0.54
     Kirchner
    -0.52
    ตรี
    -0.50
    Scaler
    -0.50
    ưỡi
    -0.50
     Crows
    -0.47
    RDP
    -0.46
    Shh
    -0.46
     vero
    -0.46
    POSITIVE LOGITS
     isle
    2.94
     Isle
    2.91
     aisle
    2.67
     Isles
    2.48
    isle
    2.48
    Isle
    2.38
     isles
    2.09
     aisles
    1.93
     pasillo
    0.73
     Ais
    0.63
    Activations Density 0.001%

    No Known Activations