© 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. 22-RES-MATRYOSHKA-DC
    7. 2923
    Prev
    Next
    INDEX
    Explanations

    words beginning with "py" followed by one or two letters

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    lapsingToolbar
    -0.57
     InputDecoration
    -0.57
     Schild
    -0.57
    interopRequire
    -0.57
    новниш
    -0.55
    Counters
    -0.55
     atque
    -0.52
     CBA
    -0.52
    ReactDOM
    -0.51
    setFrom
    -0.47
    POSITIVE LOGITS
     Py
    0.95
     py
    0.80
    Py
    0.74
     PY
    0.70
     PyObject
    0.68
    PY
    0.62
    Datuak
    0.57
     pyrite
    0.56
    thag
    0.54
    verwijspagina
    0.54
    Activations Density 0.022%

    No Known Activations