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. 14702
    Prev
    Next
    INDEX
    Explanations

    references to specific technical components, identifiers, or formatted metadata

    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
    altro
    -0.52
    ิ้ง
    -0.50
    حتی
    -0.50
     CanadaChoose
    -0.49
    pochette
    -0.48
     stesso
    -0.48
    <bos>
    -0.48
    فقط
    -0.48
     '+':
    -0.48
     nélk
    -0.48
    POSITIVE LOGITS
     تضيفلها
    1.52
    Personensuche
    1.05
     CreateTagHelper
    0.94
    awtextra
    0.91
     مشين
    0.86
    脚注の使い方
    0.85
    存于互联网档案馆
    0.82
    (!__
    0.82
     Audiodateien
    0.81
    ParallelGroup
    0.80
    Activations Density 0.116%

    No Known Activations