© 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. 8002
    Prev
    Next
    INDEX
    Explanations

    terms related to creating automated structures in a spreadsheet environment

    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
     autorytatywna
    -1.00
    jsonwebtoken
    -0.91
    tagHelperRunner
    -0.85
    SourceChecksum
    -0.85
    Havolalar
    -0.81
    __':
    -0.81
    Autoritní
    -0.81
     kaarangay
    -0.79
    ftagPool
    -0.77
    Referencie
    -0.75
    POSITIVE LOGITS
     spreadsheet
    0.85
     Spreadsheet
    0.81
    Excel
    0.73
     spreadsheets
    0.73
    xlsx
    0.72
    Spreadsheet
    0.72
    excel
    0.66
     Excel
    0.65
    PHPExcel
    0.64
    spreadsheet
    0.63
    Activations Density 0.137%

    No Known Activations