© 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. 10680
    Prev
    Next
    INDEX
    Explanations

    numerical representations related to mathematical structures or programming constructs

    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
     NDEBUG
    -0.70
     تانيه
    -0.68
    TagHelper
    -0.65
    addGap
    -0.65
    FormTagHelper
    -0.63
    astify
    -0.60
    IFICATE
    -0.59
    loài
    -0.59
     bezeichneter
    -0.59
    addContainerGap
    -0.58
    POSITIVE LOGITS
    principalTable
    0.54
    ineno
    0.45
    adple
    0.44
    mically
    0.43
    aur
    0.42
    metheus
    0.42
    bindValue
    0.40
     typelib
    0.40
    oneofs
    0.40
    istical
    0.39
    Activations Density 0.074%

    No Known Activations