© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14292
    Prev
    Next
    INDEX
    Explanations

    terms related to grouping and aggregating data in database queries

    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
    ok
    -0.51
    Epis
    -0.50
    Rhestr
    -0.46
    Temporada
    -0.45
     realistic
    -0.44
     MaterialApp
    -0.44
     Realistic
    -0.43
     cade
    -0.43
     Programme
    -0.43
    Real
    -0.42
    POSITIVE LOGITS
    出版年
    0.77
    amaño
    0.68
    preduce
    0.65
    groupby
    0.64
    getItemId
    0.63
    فایل‌لار
    0.61
    mapreduce
    0.60
     ObjectParameter
    0.59
    ApiOperation
    0.56
    riwal
    0.56
    Activations Density 0.040%

    No Known Activations