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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13781
    Prev
    Next
    INDEX
    Explanations

    patterns of numerical expressions or complex mathematical calculations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.00
    StoryboardSegue
    -0.98
     kasarigan
    -0.96
     تضيفلها
    -0.96
    featureID
    -0.96
     мәкал
    -0.96
     defaultstate
    -0.95
    :✨
    -0.93
     Réponses
    -0.93
    FTFY
    -0.92
    POSITIVE LOGITS
    v
    0.60
    begin
    0.57
    <eos>
    0.57
    <tr>
    0.57
    1
    0.54
    <bos>
    0.54
    2
    0.52
    ·
    0.52
    d
    0.51
    to
    0.50
    Activations Density 0.237%

    No Known Activations