© 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. 22-RES-MATRYOSHKA-DC
    7. 3285
    Prev
    Next
    INDEX
    Explanations

    words related to historical wars, especially world war 1

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     blog
    -0.70
     Blog
    -0.68
     tweet
    -0.65
     blogs
    -0.64
     posting
    -0.64
     CURIAM
    -0.62
    ContentAsync
    -0.62
    Hauptartikel
    -0.62
     BLOG
    -0.62
     Blogs
    -0.62
    POSITIVE LOGITS
     chapters
    0.67
    ChildScrollView
    0.65
    Includes
    0.64
     Includes
    0.64
     explores
    0.59
     للاسماء
    0.58
     Chapters
    0.57
     examines
    0.56
     tracing
    0.56
    kháu
    0.56
    Activations Density 0.321%

    No Known Activations