© 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. 24-RES-MATRYOSHKA-DC
    7. 1349
    Prev
    Next
    INDEX
    Explanations

    chunks of C code including syntax for functions, pointers, and other keywords

    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.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     responseData
    -0.56
     retVal
    -0.54
     pageNo
    -0.53
     returnValue
    -0.51
     isSuccess
    -0.49
     maxSize
    -0.49
     diverted
    -0.48
     postData
    -0.47
     startDate
    -0.46
     userList
    -0.46
    POSITIVE LOGITS
     set
    0.79
     get
    0.79
     add
    0.75
     create
    0.75
    get
    0.73
    add
    0.73
     apply
    0.72
     clear
    0.71
    create
    0.69
     put
    0.68
    Activations Density 1.229%

    No Known Activations