© 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. 4-CLT-HP
    7. 174
    Prev
    Next
    INDEX
    Explanations

    at

    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
     lavable
    -0.57
     vocales
    -0.54
     skaters
    -0.53
    Collecting
    -0.52
     ceinture
    -0.50
     endeavouring
    -0.50
     vierge
    -0.50
     occidentale
    -0.49
     learners
    -0.49
     obicei
    -0.48
    POSITIVE LOGITS
     تضيفلها
    0.81
     it
    0.66
     '\\;'
    0.62
    CppMethod
    0.56
     GenerationType
    0.54
     kaarangay
    0.54
     chi̍t
    0.54
    AtIndexPath
    0.53
     ivelany
    0.52
    [++
    0.52
    Activations Density 0.004%

    No Known Activations