© 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. 20562
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology related to integration and contours in electromagnetic fields

    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
     autorytatywna
    -0.63
    sbereich
    -0.54
     fusca
    -0.54
     universale
    -0.52
     Winaray
    -0.51
     урна
    -0.51
     attendre
    -0.50
     waiting
    -0.50
     المعيارى
    -0.50
     wars
    -0.49
    POSITIVE LOGITS
     loops
    0.60
     loop
    0.55
    Cordialement
    0.55
     looped
    0.55
     LOOP
    0.55
     Loops
    0.55
    tribal
    0.54
     itinerary
    0.54
    łaś
    0.54
     przep
    0.54
    Activations Density 0.053%

    No Known Activations