© 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. 20-CLT-HP
    7. 76431
    Prev
    Next
    INDEX
    Explanations

    places and institutions

    np_max-act-logits · 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
    GEBURTSDATUM
    -0.93
    ChildScrollView
    -0.82
    MessageTagHelper
    -0.80
    invokeLater
    -0.80
    DeleteBehavior
    -0.78
    новништво
    -0.73
    WillAppear
    -0.72
    SequentialGroup
    -0.72
    IBOutlet
    -0.71
    matchCondition
    -0.71
    POSITIVE LOGITS
     grecque
    0.45
     Buildings
    0.44
     Villas
    0.41
     gué
    0.40
     Chambers
    0.40
     lodge
    0.40
     serai
    0.40
     født
    0.38
     Man
    0.38
     lodges
    0.38
    Activations Density 0.000%

    No Known Activations