© 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. 1-RES-MATRYOSHKA-DC
    7. 1355
    Prev
    Next
    INDEX
    Explanations

    LaTeX or related formatting commands and code snippets

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    المناصب
    -0.73
     bounties
    -0.73
     Económica
    -0.71
    ารถ
    -0.67
    WriteLiteral
    -0.66
    binant
    -0.64
     plagio
    -0.63
     pitches
    -0.63
     Púb
    -0.62
     fountains
    -0.62
    POSITIVE LOGITS
    fs
    2.17
    FS
    2.02
    NS
    1.90
     fs
    1.88
    BS
    1.83
    bs
    1.79
     NS
    1.78
     FS
    1.73
    CS
    1.71
    GS
    1.71
    Activations Density 0.745%

    No Known Activations