© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15339
    Prev
    Next
    INDEX
    Explanations

    references to the word "crack" in various contexts

    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
     cracked
    -0.64
    StoryboardSegue
    -0.62
    ftagPool
    -0.61
    ismic
    -0.59
     Shoemaker
    -0.59
    ukone
    -0.57
    cracked
    -0.57
     cantons
    -0.57
    җ
    -0.56
    Cra
    -0.55
    POSITIVE LOGITS
     crack
    1.89
     Crack
    1.73
    crack
    1.62
    Crack
    1.48
     CRACK
    0.91
     crackling
    0.74
    Hentet
    0.67
    +:+
    0.57
    MENAFN
    0.56
    POP
    0.50
    Activations Density 0.008%

    No Known Activations