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. 14703
    Prev
    Next
    INDEX
    Explanations

    references to the specific classification level "Class III" in the data

    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
    iv
    -1.01
     ii
    -0.87
     iv
    -0.80
     II
    -0.68
     Ii
    -0.66
    iiii
    -0.66
    IV
    -0.65
    esModule
    -0.65
    ViewImports
    -0.63
     Iv
    -0.61
    POSITIVE LOGITS
     III
    0.97
     autorytatywna
    0.64
     Covenant
    0.61
     verst
    0.59
    Ill
    0.57
     dabei
    0.57
    XmlAccessorType
    0.57
    Beschrijving
    0.56
    III
    0.56
    JAKARTA
    0.56
    Activations Density 0.005%

    No Known Activations