© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73477
    Prev
    Next
    INDEX
    Explanations

    Technical jargon

    np_max-act-logits · 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
    ніципалі
    -0.61
     بيها
    -0.57
     Scales
    -0.53
    تل
    -0.52
     bill
    -0.52
    Biographie
    -0.51
    IUrlHelper
    -0.51
    rollup
    -0.50
    Portale
    -0.50
    ponses
    -0.50
    POSITIVE LOGITS
     propOrder
    0.72
    GTCX
    0.64
    oneofs
    0.56
    addCriterion
    0.55
     EconPapers
    0.54
    tagHelperRunner
    0.47
    RegistryLite
    0.45
     createSlice
    0.40
    sets
    0.40
    ländern
    0.40
    Activations Density 0.001%

    No Known Activations