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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12728
    Prev
    Next
    INDEX
    Explanations

    save

    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
     save
    -0.90
     Save
    -0.85
    Save
    -0.80
    save
    -0.75
     saves
    -0.75
     saved
    -0.73
     SAVE
    -0.73
     Saves
    -0.71
     Saved
    -0.66
     saving
    -0.66
    POSITIVE LOGITS
     تضيفلها
    0.85
    MockBean
    0.78
    riller
    0.71
    djangoproject
    0.71
    WaitGroup
    0.69
     vulgares
    0.64
    ezers
    0.62
    IntoConstraints
    0.62
    ighborhood
    0.61
     Ganzen
    0.61
    Activations Density 0.006%

    No Known Activations