© 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. 5-CLT-HP
    7. 703
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
     exud
    -0.46
     homeostasis
    -0.45
     polymorphism
    -0.44
     pathogenesis
    -0.41
     vesicle
    -0.40
     Systematic
    -0.40
    ostasis
    -0.40
     enthal
    -0.40
     universality
    -0.39
     biosynthesis
    -0.39
    POSITIVE LOGITS
    MessageOf
    0.85
    hyrchwyd
    0.81
    EDEFAULT
    0.76
    oa̍t
    0.75
    ंदीखरीदारी
    0.72
     समीक्षाओं
    0.71
     فريبيس
    0.71
    uxxxx
    0.70
    enderror
    0.70
     propOrder
    0.69
    Activations Density 0.000%

    No Known Activations