© 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. 31400
    Prev
    Next
    INDEX
    Explanations

    aggregates and calculations in data or SQL-like 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
    Negative Logits
    ########.
    -1.14
     kasarigan
    -0.85
    libft
    -0.84
    __":
    -0.83
    __':
    -0.82
    脚注の使い方
    -0.75
    setVerticalGroup
    -0.75
     مرئيه
    -0.74
    expandindo
    -0.73
     الحره
    -0.72
    POSITIVE LOGITS
     vọng
    0.48
     péld
    0.47
    XmlAccessType
    0.46
    ThemeOverlay
    0.45
     med
    0.44
    خره
    0.43
    ToTensor
    0.43
     Z
    0.43
     grund
    0.42
     jellemző
    0.42
    Activations Density 0.002%

    No Known Activations