© 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. 43868
    Prev
    Next
    INDEX
    Explanations

    oma

    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
    land
    -0.67
     consumer
    -0.65
    Consumer
    -0.59
    consumer
    -0.57
     consumidor
    -0.55
    al
    -0.54
    Land
    -0.49
     consommateurs
    -0.49
     rex
    -0.49
     Consumer
    -0.48
    POSITIVE LOGITS
    abstractmethod
    0.75
    NameInMap
    0.73
    SharedDtor
    0.73
    CloseOperation
    0.65
    ViewFeatures
    0.63
     initComponents
    0.63
    protoc
    0.62
     betweenstory
    0.60
     "..\..\
    0.57
    RegressionTest
    0.57
    Activations Density 0.059%

    No Known Activations