© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90862
    Prev
    Next
    INDEX
    Explanations

    none

    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
    Negative Logits
     the
    -0.70
     a
    -0.65
     Stone
    -0.62
     Winters
    -0.60
     exactly
    -0.60
     some
    -0.59
     Whip
    -0.59
     even
    -0.59
     if
    -0.59
     Grill
    -0.59
    POSITIVE LOGITS
     varandra
    0.51
    :✨
    0.48
    ItemBackground
    0.44
     högre
    0.43
    PreferredItem
    0.42
    -/
    0.39
     flesta
    0.39
     tillgäng
    0.38
     nemlig
    0.37
     stället
    0.36
    Activations Density 0.019%

    No Known Activations