© 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. 30660
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs or data types

    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
     وتسجيلات
    -0.79
    LayoutStyle
    -0.79
    GraphicsUnit
    -0.72
     ModelExpression
    -0.71
     oprot
    -0.69
    LEncoder
    -0.65
    Personendaten
    -0.65
    complexContent
    -0.64
    twimg
    -0.64
    XMLSchema
    -0.64
    POSITIVE LOGITS
     Ciò
    0.53
    cstdlib
    0.47
    noscript
    0.43
     arqu
    0.42
     handelt
    0.42
     мимо
    0.42
    permitAll
    0.41
     Aún
    0.41
    lors
    0.41
     بدان
    0.40
    Activations Density 0.028%

    No Known Activations