© 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. 25363
    Prev
    Next
    INDEX
    Explanations

    references to the term "cord," particularly in medical or biological contexts

    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
     SDLK
    -0.82
     "..\..\
    -0.79
     alu
    -0.79
     calendriers
    -0.77
     Athene
    -0.76
     Schna
    -0.74
    NavigationView
    -0.73
     EDI
    -0.72
    
    -0.71
     Menor
    -0.70
    POSITIVE LOGITS
     cord
    1.62
     Cord
    1.52
    cord
    1.40
    Cord
    1.34
     cords
    1.11
     CORD
    0.94
     Cordero
    0.94
     Cordova
    0.87
    chord
    0.77
    cordova
    0.74
    Activations Density 0.011%

    No Known Activations