© 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. 12471
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures, particularly in the context of parsing and object 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
    Not in Any Lists

    No Comments

    Negative Logits
    TintMode
    -0.91
     ExecuteAsync
    -0.79
    WireFormatLite
    -0.78
    DockStyle
    -0.78
     pinulongan
    -0.76
    millimeters
    -0.75
    webElementXpaths
    -0.68
     تضيفلها
    -0.68
     PARSER
    -0.68
     Bluestacks
    -0.66
    POSITIVE LOGITS
     ilmo
    0.47
     secondaires
    0.46
     Substanz
    0.45
     tarko
    0.45
     handled
    0.41
    mış
    0.41
     műkö
    0.41
     tache
    0.40
     instruções
    0.40
     trasparente
    0.40
    Activations Density 0.296%

    No Known Activations