© 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. 18720
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to mathematical concepts and functions

    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
    y
    -0.91
    s
    -0.86
    ay
    -0.80
    <h3>
    -0.77
    <h2>
    -0.73
    ↵↵
    -0.71
    way
    -0.68
    x
    -0.66
    ed
    -0.65
    i
    -0.65
    POSITIVE LOGITS
    XtraReports
    1.06
     pleaſure
    1.05
    ſelf
    1.05
    Спољашње
    1.04
     XCTest
    1.03
    __':
    1.02
     Anſ
    1.00
     ſeveral
    0.99
    __":
    0.99
    BibitemShut
    0.98
    Activations Density 0.091%

    No Known Activations