© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 2570
    Prev
    Next
    INDEX
    Explanations

    occurrences of quotation marks or quotations

    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
     /\.(
    -0.71
    ChildScrollView
    -0.67
    Beijos
    -0.66
    Удачи
    -0.65
     getItemId
    -0.65
    .’
    -0.64
     cyst
    -0.64
    ostante
    -0.64
     Blaise
    -0.64
     thither
    -0.63
    POSITIVE LOGITS
    ")
    1.55
    ')
    1.42
    ");
    1.26
    ');
    1.11
    ");
    
    1.08
    ").
    1.06
    ")
    
    1.06
    "));
    1.04
    "),
    1.03
    ")]
    1.00
    Activations Density 0.154%

    No Known Activations