© 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. 38301
    Prev
    Next
    INDEX
    Explanations

    Company names and code

    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
    sell
    -0.59
    MSC
    -0.53
    SWIG
    -0.53
    ening
    -0.51
     ModelExpression
    -0.50
    kor
    -0.46
    ing
    -0.45
    est
    -0.45
    nel
    -0.45
     fale
    -0.44
    POSITIVE LOGITS
     intérieure
    0.64
     skolen
    0.62
     Италијани
    0.62
    ServletException
    0.61
     aktivitet
    0.60
     godk
    0.60
     scolaires
    0.60
     nationaux
    0.59
     coroa
    0.58
     Nacionales
    0.58
    Activations Density 0.083%

    No Known Activations