© 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. 1387
    Prev
    Next
    INDEX
    Explanations

    a mix of numerical codes, abbreviated words, and substrings from programming languages, primarily extracting tokens from structured data or configuration files.

    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
                                   
    -0.87
    -0.69
    -0.59
    -0.59
                                  
    -0.58
    -0.58
     Kall
    -0.54
       
    -0.52
                                 
    -0.51
    enumi
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.66
     defaultstate
    0.65
     sachets
    0.54
                 
    0.54
     coar
    0.54
    -----------
    0.52
    ValueStyle
    0.52
    poons
    0.50
    ------------
    0.50
    anyahu
    0.50
    Activations Density 0.247%

    No Known Activations