© 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. 38928
    Prev
    Next
    INDEX
    Explanations

    Operation

    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
     Operations
    -1.34
    Operation
    -1.27
     Operation
    -1.23
    operation
    -1.22
    Operations
    -1.21
     operations
    -1.20
     operation
    -1.18
    operations
    -1.16
     OPERATIONS
    -1.08
     direction
    -1.00
    POSITIVE LOGITS
     الحره
    0.86
     GetEnumerator
    0.80
    новниш
    0.79
     itſelf
    0.79
    ंदीखरीदारी
    0.70
    antaranya
    0.70
     Efq
    0.69
     Majefty
    0.68
     متعلقه
    0.67
    లాలు
    0.66
    Activations Density 0.216%

    No Known Activations