© 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. 31883
    Prev
    Next
    INDEX
    Explanations

    references to products

    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
     PRODUCTION
    -0.99
     Production
    -0.95
     Produced
    -0.91
    production
    -0.90
    Producción
    -0.90
     production
    -0.89
    produced
    -0.88
    Production
    -0.85
     produz
    -0.85
     Producing
    -0.85
    POSITIVE LOGITS
     Produkt
    0.68
     products
    0.66
     product
    0.64
     produkt
    0.63
    Platt
    0.61
    DBObject
    0.60
    nytt
    0.60
     produtos
    0.59
     متعلقه
    0.59
    platt
    0.59
    Activations Density 0.035%

    No Known Activations