© 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. 14963
    Prev
    Next
    INDEX
    Explanations

    mentions of widgets and related programming elements in code snippets

    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
     imageNamed
    -0.73
    WithFormat
    -0.60
    amb
    -0.60
     Må
    -0.59
    SuppressMessage
    -0.59
    afp
    -0.59
    manan
    -0.59
    contentLoaded
    -0.59
    Με
    -0.59
    Ť
    -0.59
    POSITIVE LOGITS
     Widgets
    1.77
     widget
    1.74
     Widget
    1.74
    Widget
    1.71
     createState
    1.70
     widgets
    1.69
    widgets
    1.59
    widget
    1.52
    Widgets
    1.43
    WIDGET
    1.42
    Activations Density 0.002%

    No Known Activations