© 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. 20344
    Prev
    Next
    INDEX
    Explanations

    phrases that describe relationships or connections between concepts

    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
    })));
    -0.57
     useAppContext
    -0.56
    httphttps
    -0.56
     ModelExpression
    -0.55
     malin
    -0.54
    HasAnnotation
    -0.54
    солю
    -0.53
    bootstrapcdn
    -0.52
     Aeronau
    -0.52
    arau
    -0.52
    POSITIVE LOGITS
     EconPapers
    0.62
    jspx
    0.54
    </thead>
    0.54
    Similar
    0.53
    tagHelperRunner
    0.53
     benzer
    0.53
     المعيارى
    0.53
     lenker
    0.52
    onOptions
    0.52
    {§
    0.52
    Activations Density 0.060%

    No Known Activations