© 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-CLT-HP
    7. 44196
    Prev
    Next
    INDEX
    Explanations

    unexpected events

    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
     utafitiHapana
    -0.82
     HasFactory
    -0.77
     المعيارى
    -0.74
     morire
    -0.73
     initComponents
    -0.72
    comings
    -0.71
     gloire
    -0.70
     OFDb
    -0.69
     nôtre
    -0.68
     pouvoit
    -0.68
    POSITIVE LOGITS
     task
    0.49
    WebElementEntity
    0.48
     major
    0.46
     bit
    0.44
    reactstrap
    0.42
     concern
    0.41
    FTFY
    0.40
     event
    0.39
     provision
    0.39
     And
    0.39
    Activations Density 0.124%

    No Known Activations