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. 14661
    Prev
    Next
    INDEX
    Explanations

    descriptions of headache characteristics, particularly sharp or intense types

    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
     sharply
    -0.64
     sharp
    -0.50
    gpl
    -0.49
    zid
    -0.48
    kinson
    -0.48
    GPL
    -0.48
     mặt
    -0.47
    fei
    -0.47
    utri
    -0.46
     Pad
    -0.46
    POSITIVE LOGITS
    Sharp
    2.45
     Sharp
    2.44
     Sharpe
    1.32
     SHARP
    1.05
    MLLoader
    0.84
     surla
    0.75
    sharp
    0.75
     noqa
    0.69
    ⓧ
    0.69
    hdessä
    0.68
    Activations Density 0.000%

    No Known Activations