© 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. 20422
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data type cases and function calls

    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
    ArgumentParser
    -0.85
    enterOuterAlt
    -0.78
    TagMode
    -0.73
    MigrationBuilder
    -0.73
    ArrowToggle
    -0.70
    Manbalar
    -0.70
    COUVER
    -0.68
    SOUNDBITE
    -0.66
    تفصیلات
    -0.65
    AdapterFactory
    -0.64
    POSITIVE LOGITS
     fú
    0.57
    theim
    0.54
     đáp
    0.53
    damente
    0.49
     Enough
    0.48
    Enough
    0.47
    روابط
    0.47
    ξ
    0.47
    asher
    0.46
    runOnUiThread
    0.46
    Activations Density 0.010%

    No Known Activations