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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17411
    Prev
    Next
    INDEX
    Explanations

    specific programming terms and functions in software development contexts

    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
     jsPsych
    -0.79
     himo
    -0.77
     ComVisible
    -0.75
    جغرافيا
    -0.72
     Wikispecies
    -0.70
     متعلقه
    -0.70
     وتسجيلات
    -0.69
     '\\;'
    -0.69
    OGND
    -0.68
    orsese
    -0.68
    POSITIVE LOGITS
     or
    0.50
     vital
    0.44
    frem
    0.44
    طل
    0.43
     Chaudh
    0.42
    matchCondition
    0.42
    MergeFrom
    0.42
     South
    0.41
    TagMode
    0.41
    <eos>
    0.41
    Activations Density 0.104%

    No Known Activations