© 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. 26754
    Prev
    Next
    INDEX
    Explanations

    programming or scripting language syntax related to function or method definitions

    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
     autorytatywna
    -0.80
    zerne
    -0.75
     pylori
    -0.73
    IVEREF
    -0.72
     समीक्षक
    -0.71
    MLLoader
    -0.69
     Italijani
    -0.68
    
    -0.68
    nologue
    -0.67
    opcional
    -0.66
    POSITIVE LOGITS
    史
    0.55
    BeginContext
    0.50
    死
    0.49
     vz
    0.48
    apt
    0.46
    <bos>
    0.45
     sper
    0.45
     Scri
    0.45
     المعيارى
    0.44
    efte
    0.44
    Activations Density 0.008%

    No Known Activations