© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92249
    Prev
    Next
    INDEX
    Explanations

    ${

    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
     nahilalakip
    -1.27
     الرياضيه
    -0.90
    पया
    -0.88
     otomatig
    -0.87
    !*\
    -0.85
    Portail
    -0.84
     propOrder
    -0.82
    rungsseite
    -0.77
    ंदीखरीदारी
    -0.75
    TestingModule
    -0.74
    POSITIVE LOGITS
     I
    0.62
     
    0.60
    ↵↵
    0.54
     El
    0.49
     F
    0.48
     author
    0.48
    ↵
    0.47
     A
    0.46
    <eos>
    0.45
     Her
    0.45
    Activations Density 1.986%

    No Known Activations