Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14631
    Prev
    Next
    INDEX
    Explanations

    references to copyright exemption or fair use related to copyrighted works

    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
    unehmen
    -0.69
    netinet
    -0.65
    !("{}",
    -0.65
    parameters
    -0.65
    InjectAttribute
    -0.63
    OGND
    -0.63
    LEncoder
    -0.63
     تضيفلها
    -0.62
     للاسماء
    -0.61
     вікі
    -0.61
    POSITIVE LOGITS
    rido
    1.13
    empted
    0.91
    sier
    0.90
    itzer
    0.72
    empt
    0.71
    thanol
    0.70
    emption
    0.70
    parameter
    0.68
    rungsseite
    0.64
    minded
    0.60
    Activations Density 0.018%

    No Known Activations