© 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. 15842
    Prev
    Next
    INDEX
    Explanations

    patterns in structured data or code

    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
    setVerticalGroup
    -0.60
    pyl
    -0.45
     WRAP
    -0.45
    ValueStyle
    -0.45
    ιδ
    -0.44
    EOL
    -0.44
     rowspan
    -0.42
    ẳng
    -0.42
     arras
    -0.42
    ipal
    -0.42
    POSITIVE LOGITS
    oredCriteria
    0.74
     kasarigan
    0.72
    InjectAttribute
    0.67
     विश्वसनीयता
    0.67
     CWE
    0.64
     Exactos
    0.63
    webElementGuid
    0.62
    principalColumn
    0.60
    XmlAccessType
    0.60
     CURIAM
    0.59
    Activations Density 0.092%

    No Known Activations