© 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. 12106
    Prev
    Next
    INDEX
    Explanations

    punctuation that indicates the end of encapsulated expressions or sections of code

    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
     jadx
    -0.66
     ThemeData
    -0.62
     ویکی‌پدیای
    -0.58
     NSCoder
    -0.58
    Datuak
    -0.57
     Italijani
    -0.54
    fjspx
    -0.53
    
    -0.53
    ulario
    -0.52
     NUKAT
    -0.52
    POSITIVE LOGITS
    AutoScale
    0.56
    Somehow
    0.56
    //
    0.53
     متعلقه
    0.53
    AccessFile
    0.52
     Schmel
    0.51
    /******/
    0.50
    GenerationType
    0.49
     lẫn
    0.49
    nonumber
    0.49
    Activations Density 0.001%

    No Known Activations