© 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. 18637
    Prev
    Next
    INDEX
    Explanations

    coding structures and specific commands within programming or assembly 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
    Negative Logits
    matum
    -0.58
     Италијани
    -0.57
     تضيفلها
    -0.54
    CodeAttribute
    -0.52
    HtmlAttribute
    -0.52
     custard
    -0.51
     roux
    -0.51
    unmodifiable
    -0.47
     الدولى
    -0.47
    numerusform
    -0.46
    POSITIVE LOGITS
     stack
    0.83
    stack
    0.76
    Stack
    0.75
     Stack
    0.74
     stacks
    0.71
    STACK
    0.71
    栈
    0.69
    BackStack
    0.67
     invokingState
    0.62
    sidemargin
    0.61
    Activations Density 0.014%

    No Known Activations