© 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. 22-RES-MATRYOSHKA-DC
    7. 3000
    Prev
    Next
    INDEX
    Explanations

    mentions of code files and code syntax, as well as suggestions to create something.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    Code
    -0.49
    code
    -0.44
     anything
    -0.42
     operazioni
    -0.40
    Anything
    -0.40
    numeros
    -0.40
     meines
    -0.40
    /
    -0.39
     näch
    -0.39
    /...
    -0.39
    POSITIVE LOGITS
    MigrationBuilder
    0.86
    AndEndTag
    0.86
     separate
    0.78
    separate
    0.73
     seperate
    0.73
     SEPAR
    0.69
    tagHelperRunner
    0.68
    makeConstraints
    0.66
     StatefulWidget
    0.66
     surla
    0.66
    Activations Density 0.380%

    No Known Activations