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. 14592
    Prev
    Next
    INDEX
    Explanations

    references to helping or providing assistance

    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
    Supporting
    -0.79
     LUMP
    -0.73
     supporting
    -0.72
     Supporting
    -0.72
    supporting
    -0.70
    __(/*!
    -0.66
    abetes
    -0.64
    колай
    -0.64
     חיצוניים
    -0.63
    dificio
    -0.60
    POSITIVE LOGITS
     helps
    1.34
     Helps
    1.18
    Helps
    1.13
    helps
    1.03
     autorytatywna
    0.63
    尽量
    0.62
     try
    0.59
     helpt
    0.59
     works
    0.58
     improves
    0.58
    Activations Density 0.002%

    No Known Activations