© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 95027
    Prev
    Next
    INDEX
    Explanations

    population, subsidies

    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
    Population
    -0.85
     population
    -0.84
     Population
    -0.71
    population
    -0.70
     Bevölkerung
    -0.60
     pinulongan
    -0.60
    chable
    -0.58
    kegaard
    -0.57
    .";
    
    -0.56
     demographic
    -0.55
    POSITIVE LOGITS
    setupUi
    0.56
    CloseOperation
    0.53
    AttributeSet
    0.48
     recue
    0.48
    WriteTagHelper
    0.47
     Drapeau
    0.47
     stabilité
    0.46
     Avian
    0.46
     cellpadding
    0.45
    RegressionTest
    0.45
    Activations Density 1.278%

    No Known Activations