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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2894
    Prev
    Next
    INDEX
    Explanations

    numbers and addresses

    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
     conseguenza
    -0.62
     hiér
    -0.61
     autorytatywna
    -0.60
     científicas
    -0.59
     piú
    -0.57
     avulla
    -0.57
     toepassing
    -0.57
     degrés
    -0.57
     prière
    -0.56
     feroit
    -0.56
    POSITIVE LOGITS
    LookAnd
    0.61
     thing
    0.59
     episode
    0.57
     createSprite
    0.57
    scissors
    0.56
     sphere
    0.56
     neutrino
    0.56
     photon
    0.54
     circle
    0.53
    Enllaces
    0.53
    Activations Density 0.005%

    No Known Activations