© 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. 22751
    Prev
    Next
    INDEX
    Explanations

    references to quantities and measurements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Millar
    -0.84
    oara
    -0.84
     ARA
    -0.83
     sputnik
    -0.79
    Datuak
    -0.79
     Maia
    -0.78
    Portail
    -0.77
     Paragon
    -0.77
     Gibbon
    -0.77
    cookieParser
    -0.77
    POSITIVE LOGITS
     quantity
    1.06
     quantities
    1.05
     Quantity
    0.96
     Quantities
    0.90
    quantity
    0.90
    Quantity
    0.87
    Qty
    0.78
    antity
    0.75
    qty
    0.75
     qty
    0.73
    Activations Density 0.004%

    No Known Activations