© 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. 0-CLT-HP
    7. 94034
    Prev
    Next
    INDEX
    Explanations

    Academic/technical terminology

    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
     framework
    -0.87
     methodology
    -0.79
     protocol
    -0.74
     literature
    -0.73
    ſelves
    -0.66
    MessageTagHelper
    -0.65
    "]);
    -0.63
    ſelf
    -0.62
    framework
    -0.62
     terminology
    -0.60
    POSITIVE LOGITS
     accident
    0.60
    зулта
    0.57
    artifactId
    0.54
     Accesat
    0.53
     pitä
    0.53
     of
    0.52
     founded
    0.52
     excuses
    0.52
    الإنجليزية
    0.52
    στα
    0.50
    Activations Density 0.163%

    No Known Activations