© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98198
    Prev
    Next
    INDEX
    Explanations

    to

    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
     المعيارى
    -0.86
     destinées
    -0.66
     Italijanski
    -0.66
     électroniques
    -0.65
    Personensuche
    -0.64
     énergé
    -0.64
    UnitTesting
    -0.60
     насељу
    -0.58
     venons
    -0.57
     projecting
    -0.57
    POSITIVE LOGITS
     form
    1.01
     share
    0.60
    form
    0.58
     present
    0.57
     constitute
    0.56
    ge
    0.56
     from
    0.56
     fom
    0.55
     one
    0.50
     build
    0.49
    Activations Density 0.006%

    No Known Activations