© 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. 4-CLT-HP
    7. 3221
    Prev
    Next
    INDEX
    Explanations

    code/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
     rospy
    -0.59
     Haines
    -0.52
     télévis
    -0.52
    øg
    -0.50
    ėd
    -0.48
     Nair
    -0.48
     الترك
    -0.48
    ringer
    -0.48
     Saal
    -0.47
     richt
    -0.47
    POSITIVE LOGITS
    はじめに
    0.62
    šinou
    0.57
    parsedMessage
    0.54
     <=",
    0.52
    RegressionTest
    0.52
     propOrder
    0.50
     JADX
    0.49
    ConstraintMaker
    0.48
    <bos>
    0.48
    lankton
    0.48
    Activations Density 0.002%

    No Known Activations