© 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. 20-CLT-HP
    7. 74802
    Prev
    Next
    INDEX
    Explanations

    times

    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
    phism
    -0.54
    cuss
    -0.51
     stund
    -0.49
     Phry
    -0.49
     позна
    -0.46
     muualla
    -0.45
    कों
    -0.44
     form
    -0.44
    otesi
    -0.44
     IndexPath
    -0.44
    POSITIVE LOGITS
    :✨
    0.68
     last
    0.68
     are
    0.66
    enumi
    0.64
    ValueStyle
    0.63
    RefNanny
    0.60
    last
    0.59
     come
    0.58
     Equal
    0.56
    iNdEx
    0.55
    Activations Density 0.000%

    No Known Activations