© 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. 32019
    Prev
    Next
    INDEX
    Explanations

    references to mathematical functions and their solutions within a variational context

    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
     فريبيس
    -0.88
     EconPapers
    -0.74
     BoxFit
    -0.73
    NewUrlParser
    -0.71
    +#+#
    -0.71
     ffilmiau
    -0.71
    iNdEx
    -0.70
    httphttps
    -0.69
    IsMutable
    -0.68
    χρι
    -0.68
    POSITIVE LOGITS
    MigrationBuilder
    0.58
    most
    0.48
    μορ
    0.48
     didst
    0.47
     Heat
    0.46
     expected
    0.45
    ắp
    0.45
    Gren
    0.45
    umman
    0.45
    oznam
    0.44
    Activations Density 0.037%

    No Known Activations