© 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. 21272
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or theorems related to dimensions and ideal structures

    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
    StringUtil
    -0.45
    urlopen
    -0.43
    ing
    -0.43
    stick
    -0.43
    TestUtil
    -0.42
    mey
    -0.41
     Ar
    -0.40
    iana
    -0.40
    staat
    -0.40
    ता
    -0.40
    POSITIVE LOGITS
    клопе
    1.11
     שוליים
    0.95
    principalTable
    0.94
    Hochspringen
    0.91
    SharedDtor
    0.91
     MainAxisSize
    0.88
    sizeCache
    0.87
     BorderSide
    0.87
    WireFormatLite
    0.86
     Савезне
    0.85
    Activations Density 0.016%

    No Known Activations