© 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. 18834
    Prev
    Next
    INDEX
    Explanations

    parentheses or related symbols used in programming and API response structures

    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
    Portale
    -0.69
    {}",
    -0.69
    MessageTagHelper
    -0.67
    istle
    -0.63
    /−
    -0.63
     censiti
    -0.62
    pecia
    -0.60
    PLING
    -0.58
     Wul
    -0.58
     bint
    -0.57
    POSITIVE LOGITS
    Kaynakça
    0.63
     Hec
    0.60
     تضيفلها
    0.60
    Hochspringen
    0.58
    ChromeDriver
    0.57
     useRouter
    0.56
     Polic
    0.54
    Données
    0.54
     Pyram
    0.54
     Sabo
    0.54
    Activations Density 0.002%

    No Known Activations