© 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. 0-CLT-HP
    7. 40113
    Prev
    Next
    INDEX
    Explanations

    chor

    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
     chor
    -0.76
     chorus
    -0.68
     cranks
    -0.67
     Ox
    -0.59
    chor
    -0.56
    cla
    -0.53
     ox
    -0.53
     crankshaft
    -0.52
     palmar
    -0.50
    timedia
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.91
    ValueStyle
    0.83
    UrlResolution
    0.77
    TagHelper
    0.70
    httphttps
    0.70
     ProtoMessage
    0.68
    contentLoaded
    0.67
     ligiloj
    0.67
    Personensuche
    0.66
     @"/
    0.66
    Activations Density 0.317%

    No Known Activations