© 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. 11719
    Prev
    Next
    INDEX
    Explanations

    test-related terminology and 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
    ásban
    -0.63
    ništ
    -0.60
     незавершена
    -0.57
     Examinations
    -0.57
    localctx
    -0.57
    mybatisplus
    -0.57
    ‍♀️
    -0.56
    SignedIn
    -0.55
     examinations
    -0.54
     travaux
    -0.54
    POSITIVE LOGITS
    RegressionTest
    0.69
     Wilayah
    0.49
    makeText
    0.48
    even
    0.47
    prompt
    0.47
     CSF
    0.47
    withstanding
    0.45
    itous
    0.45
    LPD
    0.45
    writeln
    0.45
    Activations Density 0.027%

    No Known Activations