© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41622
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
     démocr
    -0.73
     étoit
    -0.71
    ÉD
    -0.70
     dévelo
    -0.69
     citoy
    -0.69
    ounted
    -0.68
     inégal
    -0.68
     culturelles
    -0.68
     commerciaux
    -0.67
     enfans
    -0.67
    POSITIVE LOGITS
    parsedMessage
    0.52
    TypedDataSet
    0.50
    ge
    0.45
     recognised
    0.42
    "})
    0.42
     "))
    0.42
     hellen
    0.41
     '))
    0.41
    retweeted
    0.41
     colab
    0.41
    Activations Density 0.480%

    No Known Activations