© 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. 94888
    Prev
    Next
    INDEX
    Explanations

    formal reports/procedures

    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
     Than
    -0.65
     Edition
    -0.63
     Series
    -0.59
     System
    -0.58
     Collection
    -0.56
     Framework
    -0.55
     Synd
    -0.55
     Network
    -0.54
     Association
    -0.52
     Meets
    -0.52
    POSITIVE LOGITS
     uſed
    0.68
     include
    0.68
     whoſe
    0.64
     muſt
    0.63
     célèbres
    0.62
     quoque
    0.62
     verschillen
    0.59
     vary
    0.59
     myſelf
    0.58
     ſhould
    0.57
    Activations Density 0.068%

    No Known Activations