© 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. 6120
    Prev
    Next
    INDEX
    Explanations

    descriptions of experimental procedures and methods

    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
    ::~
    -0.46
    Bronnen
    -0.46
    észet
    -0.46
    براير
    -0.43
     phẩm
    -0.43
     siquiera
    -0.43
     even
    -0.40
    endsection
    -0.40
     mandato
    -0.40
    antar
    -0.39
    POSITIVE LOGITS
    Geplaatst
    0.77
     defaultstate
    0.64
    RTLU
    0.63
    حياتها
    0.61
     onCreateView
    0.61
     Erişim
    0.61
    Архівовано
    0.60
     resourceCulture
    0.58
    ⓧ
    0.58
     NUKAT
    0.56
    Activations Density 0.218%

    No Known Activations