© 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. 91093
    Prev
    Next
    INDEX
    Explanations

    web content

    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
    rungsseite
    -0.65
    <bos>
    -0.61
    XmlAccessType
    -0.61
    UnusedPrivate
    -0.57
    ReusableCell
    -0.57
     Meksiku
    -0.54
     Мексичка
    -0.50
    :
    -0.48
    URLException
    -0.48
    IntoConstraints
    -0.48
    POSITIVE LOGITS
     ways
    0.59
     dedans
    0.57
    anmoins
    0.57
     you
    0.57
    OGND
    0.56
    activités
    0.54
     matters
    0.54
     вами
    0.54
    aspects
    0.54
    Ways
    0.53
    Activations Density 0.001%

    No Known Activations