© 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. 15005
    Prev
    Next
    INDEX
    Explanations

    programming language constructs related to function definitions and attributes

    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
    URLException
    -0.62
    yntaxException
    -0.60
    Antar
    -0.54
     Jara
    -0.53
    AnchorTagHelper
    -0.52
    giveness
    -0.51
    FormTagHelper
    -0.50
    şehir
    -0.50
     PhpStorm
    -0.50
     hã
    -0.49
    POSITIVE LOGITS
    ніципалі
    0.76
    CppMethod
    0.72
     مشين
    0.68
     فريبيس
    0.68
    ValueStyle
    0.68
    LLVM
    0.65
     StatefulWidget
    0.65
    migrationBuilder
    0.64
    Rhestr
    0.64
     Stall
    0.63
    Activations Density 0.001%

    No Known Activations