© 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. 31948
    Prev
    Next
    INDEX
    Explanations

    references to file modifications and changes in the context of conditional HTTP requests

    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
     ComVisible
    -0.70
    migrationBuilder
    -0.66
    WithIOException
    -0.62
    !*\
    -0.57
     Wikimedijinoj
    -0.57
    <?
    -0.56
     RESERV
    -0.52
     uintptr
    -0.52
    ThroughAttribute
    -0.52
    fanart
    -0.51
    POSITIVE LOGITS
    Change
    0.63
     Change
    0.57
     CHANGE
    0.54
    Difference
    0.52
    UnknownFieldSet
    0.52
     complacency
    0.52
     Difference
    0.51
     change
    0.51
    changes
    0.50
     incremental
    0.50
    Activations Density 0.135%

    No Known Activations