© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 88
    Prev
    Next
    INDEX
    Explanations

    the words "in", "to", "from", "as", "on", "with", "for", "by", "between", "than", "while", "above", "during", "containing", "like", "of", "when", "onto", "through", "

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Florentine
    -0.61
     arbejds
    -0.59
    P
    -0.58
    E
    -0.58
    W
    -0.57
     GABA
    -0.57
     VEGF
    -0.57
     creatine
    -0.55
     Hadrian
    -0.54
    S
    -0.54
    POSITIVE LOGITS
     the
    1.41
    )";
    0.98
    Από
    0.98
    .}(
    0.97
     its
    0.96
    AddTagHelper
    0.96
    Για
    0.95
    readFileSync
    0.93
    )':
    0.92
    `,
    0.92
    Activations Density 8.830%

    No Known Activations