© 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. 91164
    Prev
    Next
    INDEX
    Explanations

    and lists

    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
    cvtColor
    -0.47
     giudi
    -0.47
    impri
    -0.47
     ώ
    -0.46
    execSQL
    -0.44
    τώ
    -0.44
    tto
    -0.44
    knew
    -0.44
    mahaman
    -0.44
    ùm
    -0.44
    POSITIVE LOGITS
    AndEndTag
    0.95
    tagHelperRunner
    0.92
    SBATCH
    0.78
     AssemblyProduct
    0.75
     المعيارى
    0.74
    
    0.71
    WriteTagHelper
    0.70
     OFDb
    0.68
     <=",
    0.66
     चीज़ों
    0.66
    Activations Density 1.866%

    No Known Activations