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. 14689
    Prev
    Next
    INDEX
    Explanations

    references to the act of retaining or keeping something

    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
     retain
    -0.66
    webElementGuid
    -0.49
    istar
    -0.48
    ">>
    -0.48
     undefined
    -0.46
     retaining
    -0.46
     isolé
    -0.46
    COUVER
    -0.45
     jadi
    -0.45
    grà
    -0.45
    POSITIVE LOGITS
     retained
    1.92
     ویکی‌پدیا
    0.81
    tained
    0.81
     للاسماء
    0.69
    ByPrimaryKey
    0.68
    ViewChild
    0.62
    IBOutlet
    0.61
     held
    0.60
    held
    0.60
    tymologie
    0.59
    Activations Density 0.001%

    No Known Activations