© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38329
    Prev
    Next
    INDEX
    Explanations

    other

    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
    InSection
    -0.63
    rungsseite
    -0.53
     enjeux
    -0.51
     attentes
    -0.50
     مُعرِّف
    -0.49
     réfugiés
    -0.49
     témoins
    -0.48
     câbles
    -0.48
    はじめに
    -0.47
    cloudflare
    -0.47
    POSITIVE LOGITS
     directions
    0.92
     ways
    0.83
     respects
    0.69
     Directions
    0.65
    directions
    0.65
    GHIJKLM
    0.64
     manners
    0.63
     circumstances
    0.61
    #+#
    0.60
     myſelf
    0.59
    Activations Density 0.137%

    No Known Activations