© 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. 6045
    Prev
    Next
    INDEX
    Explanations

    Instructions

    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
    <bos>
    -0.88
     Мексичка
    -0.62
    GTCX
    -0.57
    iprot
    -0.57
    ItemBackground
    -0.56
    хьтан
    -0.56
     llegando
    -0.55
     يتيمه
    -0.53
     cambiando
    -0.53
     comprando
    -0.51
    POSITIVE LOGITS
     you
    0.73
     locate
    0.65
     start
    0.53
     migrate
    0.52
     ignore
    0.52
     Monfieur
    0.52
     find
    0.52
    Hauptartikel
    0.52
     roam
    0.51
    neſs
    0.50
    Activations Density 0.007%

    No Known Activations