© 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. 15541
    Prev
    Next
    INDEX
    Explanations

    sel

    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
     تضيفلها
    -0.55
     дописавши
    -0.53
    olato
    -0.53
    IBLES
    -0.52
     Pula
    -0.52
     pula
    -0.52
    BeginContext
    -0.51
     AssemblyProduct
    -0.50
     BorderRadius
    -0.49
     "../../../
    -0.49
    POSITIVE LOGITS
    msgTypes
    0.54
    Portály
    0.54
    GEBURTSDATUM
    0.53
    mapreduce
    0.52
    acjach
    0.49
    RegressionTest
    0.48
    featureID
    0.48
    CONCURRENT
    0.48
     propOrder
    0.47
     gynhyrchwyd
    0.45
    Activations Density 0.114%

    No Known Activations