© 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. 10418
    Prev
    Next
    INDEX
    Explanations

    test assertions and results in code snippets, particularly focusing on equality checks

    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
     propOrder
    -0.73
    niająca
    -0.72
    帖最后由
    -0.67
     архивлан
    -0.65
    RepeatedField
    -0.65
    crypted
    -0.64
     betweenstory
    -0.64
    titleMargin
    -0.63
    webElementGuid
    -0.61
    دانشنامهٔ
    -0.61
    POSITIVE LOGITS
    Races
    0.62
    Enllaces
    0.54
    FloatField
    0.52
    banco
    0.50
    ('|
    0.50
     CURIAM
    0.49
    ('\\
    0.49
    parsedMessage
    0.47
     Races
    0.46
     contextLoads
    0.46
    Activations Density 0.009%

    No Known Activations