© 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. 1-CLT-HP
    7. 16228
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     release
    -1.39
     released
    -1.32
     releases
    -1.23
    release
    -1.21
     releasing
    -1.17
     Release
    -1.16
    released
    -1.12
    Release
    -1.11
    Released
    -1.07
     Released
    -1.05
    POSITIVE LOGITS
    SequentialGroup
    0.74
     الرياضيه
    0.69
     فريبيس
    0.68
     MAI
    0.67
    EndTag
    0.67
    reamble
    0.66
    :✨
    0.65
    Hentet
    0.65
    PARATUS
    0.64
    aarrggbb
    0.64
    Activations Density 0.038%

    No Known Activations