© 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. 0-CLT-HP
    7. 95430
    Prev
    Next
    INDEX
    Explanations

    Medical imaging and databases

    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
     central
    -0.68
    scale
    -0.66
    db
    -0.65
     db
    -0.58
    DB
    -0.57
     Church
    -0.57
     scale
    -0.56
    central
    -0.55
     centrales
    -0.50
    Scale
    -0.50
    POSITIVE LOGITS
    EDEFAULT
    1.28
     تضيفلها
    1.13
    ſelf
    1.10
     Houſe
    1.08
     houſe
    1.07
     Theſe
    1.07
     greateſt
    1.06
     itſelf
    1.05
     Monfieur
    1.05
    ſelves
    1.04
    Activations Density 2.417%

    No Known Activations