© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3380
    Prev
    Next
    INDEX
    Explanations

    weather forecasts

    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
    Javadoc
    -0.71
    routeProvider
    -0.55
     vulgares
    -0.54
    Revenir
    -0.50
    ngdoc
    -0.50
    Bước
    -0.48
    posedge
    -0.48
     veremos
    -0.48
    ieteur
    -0.48
    amaño
    -0.47
    POSITIVE LOGITS
     to
    0.84
    BeginContext
    0.64
     WET
    0.56
     HasFactory
    0.53
    ulose
    0.52
    ddle
    0.52
     RequestMethod
    0.50
    AddTagHelper
    0.49
    ✭✭
    0.48
    брь
    0.47
    Activations Density 0.004%

    No Known Activations