© 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. 23423
    Prev
    Next
    INDEX
    Explanations

    SQL query syntax elements, particularly related to selection and grouping

    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
     surla
    -0.88
     loch
    -0.77
     intptr
    -0.75
     kasarigan
    -0.74
    ագրություններ
    -0.73
    PropertyGroup
    -0.72
    posedge
    -0.70
    Vidite
    -0.69
     OFDb
    -0.69
    ⓘ
    -0.69
    POSITIVE LOGITS
    .*")]
    0.76
     original
    0.46
     over
    0.43
     is
    0.43
     normally
    0.42
     semula
    0.41
     pener
    0.41
     sendiri
    0.41
     awalnya
    0.40
    setToolTip
    0.40
    Activations Density 0.004%

    No Known Activations