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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14620
    Prev
    Next
    INDEX
    Explanations

    thermodynamics and polarization

    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
     thermodynamic
    -0.98
     thermodynamics
    -0.68
    oredCriteria
    -0.63
     AssemblyCompany
    -0.58
     Thermodynamics
    -0.55
    CJK
    -0.52
    LayoutStyle
    -0.50
    HtmlAttribute
    -0.50
    ImageContext
    -0.50
     تضيفلها
    -0.50
    POSITIVE LOGITS
    ally
    0.69
    ALLY
    0.56
     EconPapers
    0.48
     Integration
    0.47
    ality
    0.45
    nalité
    0.45
     Tirol
    0.44
     Gentlemen
    0.43
    ers
    0.43
    ulators
    0.43
    Activations Density 0.030%

    No Known Activations