© 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. 22764
    Prev
    Next
    INDEX
    Explanations

    instructions, particularly related to mathematical or programming commands

    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
     themſelves
    -0.50
     centrales
    -0.48
     ύ
    -0.45
    Pearson
    -0.45
    angeran
    -0.45
     centrum
    -0.45
    راك
    -0.45
     ejus
    -0.44
     intest
    -0.44
     Sö
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.84
     يتيمه
    0.82
    SharedCtor
    0.79
    
    0.79
     initComponents
    0.78
    expandindo
    0.74
     transfieras
    0.73
    SourceChecksum
    0.71
     getItemCount
    0.71
     مرئيه
    0.69
    Activations Density 0.015%

    No Known Activations