© 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. 20387
    Prev
    Next
    INDEX
    Explanations

    discussions related to medical treatment and research strategies

    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
     popolare
    -0.59
     meren
    -0.58
     interpolated
    -0.56
     popolari
    -0.54
     conva
    -0.54
     ViewGroup
    -0.52
     volunteered
    -0.52
     äußer
    -0.52
     Aeronautical
    -0.51
     newspapers
    -0.50
    POSITIVE LOGITS
    ьаж
    0.87
     lenker
    0.79
    queryInterface
    0.74
    ContentAsync
    0.73
    èdia
    0.73
    Билгалдахарш
    0.70
    WebVitals
    0.70
     estimés
    0.70
    Datuak
    0.69
    تقاوى
    0.68
    Activations Density 0.421%

    No Known Activations