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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40823
    Prev
    Next
    INDEX
    Explanations

    crash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crashes
    -0.86
     crashed
    -0.85
    ns
    -0.85
     crashing
    -0.82
     crash
    -0.80
     Crash
    -0.64
     Cras
    -0.60
     ns
    -0.60
    cras
    -0.60
    Crash
    -0.59
    POSITIVE LOGITS
     itſelf
    0.90
     themſelves
    0.81
     myſelf
    0.77
     theſe
    0.74
     ostavi
    0.74
     ſta
    0.74
     تضيفلها
    0.72
    ChildIndex
    0.72
     ་་
    0.72
    protoimpl
    0.69
    Activations Density 0.231%

    No Known Activations