© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 181
    Prev
    Next
    INDEX
    Explanations

    starting

    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
     समीक्षक
    -0.97
     Efq
    -0.84
     '\\;'
    -0.77
    ftagPool
    -0.77
    WriteTagHelper
    -0.75
     Monfieur
    -0.73
    Personensuche
    -0.73
    __*/
    -0.71
    typeorm
    -0.70
    twimg
    -0.69
    POSITIVE LOGITS
     point
    0.52
     block
    0.44
    วย
    0.43
     off
    0.38
     bench
    0.37
     board
    0.37
     ground
    0.36
    ingtones
    0.36
    ging
    0.34
    rek
    0.34
    Activations Density 0.003%

    No Known Activations