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. 14734
    Prev
    Next
    INDEX
    Explanations

    references to the concept of folding or the process of folding

    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
     roll
    -1.80
    roll
    -1.59
    Roll
    -1.58
     Roll
    -1.57
     rolls
    -1.57
     rolled
    -1.55
     ROLL
    -1.49
    ROLL
    -1.48
     rolling
    -1.44
    rolls
    -1.39
    POSITIVE LOGITS
    fold
    1.61
     threefold
    0.63
    folds
    0.56
    ly
    0.53
     twofold
    0.53
    WebVitals
    0.50
     times
    0.48
    lemented
    0.47
    peq
    0.47
    yntaxException
    0.47
    Activations Density 0.003%

    No Known Activations