Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14696
    Prev
    Next
    INDEX
    Explanations

    references to Columbus associated with repeated mentions of the city

    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
    tagHelperRunner
    -0.66
     Associated
    -0.66
    tvguidetime
    -0.66
    SceneManagement
    -0.63
    Associated
    -0.61
    Hochspringen
    -0.60
    hips
    -0.58
    脚注の使い方
    -0.57
    msgTypes
    -0.57
     glutamate
    -0.56
    POSITIVE LOGITS
     CN
    1.04
     Columbus
    0.94
    Columbus
    0.87
     (;
    0.77
     checksum
    0.76
    richTextPanel
    0.68
    তথ্যসূত্র
    0.63
     Collins
    0.62
     للاسماء
    0.60
    BufferException
    0.57
    Activations Density 0.005%

    No Known Activations