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. 14674
    Prev
    Next
    INDEX
    Explanations

    the presence and degree of skewness in the distribution

    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
     skeletal
    -1.33
     skeleton
    -1.26
    skeleton
    -1.21
     Skeletal
    -1.15
     Skeleton
    -0.96
    Skeleton
    -0.93
     skeletons
    -0.93
     esqueleto
    -0.88
    letal
    -0.82
     secretory
    -0.81
    POSITIVE LOGITS
     skew
    2.38
    skew
    1.95
     ske
    1.95
     skewed
    1.52
     Ske
    1.08
    ske
    0.88
     skewers
    0.81
    Ske
    0.80
    webElementGuid
    0.63
    IsPostBack
    0.58
    Activations Density 0.002%

    No Known Activations