© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 547
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming control structures and error handling in 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
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.46
    ,
    -0.45
     
    -0.44
     &
    -0.42
     la
    -0.40
     backpack
    -0.40
     -
    -0.39
    (
    -0.39
     is
    -0.37
     +
    -0.37
    POSITIVE LOGITS
    Hochspringen
    1.12
     дописавши
    1.05
     ExecuteAsync
    1.04
     مشين
    1.02
    IntoConstraints
    1.00
    \}\\
    1.00
    expandindo
    0.94
     חיצוניים
    0.92
    MigrationBuilder
    0.91
     متعلقه
    0.88
    Activations Density 0.577%

    No Known Activations