© 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. 11795
    Prev
    Next
    INDEX
    Explanations

    informational commands or operations in a programming context

    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
    ftagPool
    -0.83
    sizeCache
    -0.79
    KommentareTeilen
    -0.76
     CreateTagHelper
    -0.73
    djangoproject
    -0.71
    mybatisplus
    -0.71
    Personensuche
    -0.70
    Geplaatst
    -0.67
    autaire
    -0.66
    argout
    -0.65
    POSITIVE LOGITS
     calendriers
    0.58
    რო
    0.53
     jLabel
    0.52
    BACA
    0.51
    esterno
    0.50
    :^{
    0.47
    !("{}",
    0.46
     Gleaner
    0.46
    ++.
    0.46
    ++)
    0.44
    Activations Density 0.007%

    No Known Activations