© 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. 4-CLT-HP
    7. 1866
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    ########.
    -0.73
     vägen
    -0.65
     stället
    -0.61
     оригіналу
    -0.59
     oprot
    -0.59
     culturelles
    -0.58
     iprot
    -0.57
     banques
    -0.57
     démocr
    -0.56
     jorden
    -0.56
    POSITIVE LOGITS
     Hez
    0.50
     Hanford
    0.48
    therly
    0.47
    cences
    0.47
     Whittier
    0.47
     Moritz
    0.45
    wegg
    0.44
     Chaco
    0.44
     findBy
    0.44
    exports
    0.43
    Activations Density 0.006%

    No Known Activations