© 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. 6-RES-MATRYOSHKA-DC
    7. 1374
    Prev
    Next
    INDEX
    Explanations

    parenthetical expressions and mathematical symbols

    oai_token-act-pair · gemini-2.0-flash
    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
    +#+
    -0.66
     الرياضيه
    -0.60
    |}{}
    -0.59
    первых
    -0.57
    alach
    -0.54
    rophi
    -0.53
     sockaddr
    -0.53
    Cathy
    -0.53
     Balo
    -0.52
     Dafür
    -0.52
    POSITIVE LOGITS
    PerformLayout
    0.90
    parsedMessage
    0.87
    ViewFeatures
    0.82
    Kaynakça
    0.79
    Personendaten
    0.76
    WithIOException
    0.76
    Diweddarwch
    0.75
     continúas
    0.73
     &___
    0.73
    IntoConstraints
    0.68
    Activations Density 3.096%

    No Known Activations