© 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. 5-CLT-HP
    7. 91819
    Prev
    Next
    INDEX
    Explanations

    EN

    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
     Microbiology
    -0.59
    ilingual
    -0.57
    BAND
    -0.56
    Band
    -0.56
     theſe
    -0.55
     himſelf
    -0.54
     Triassic
    -0.54
     raiſ
    -0.53
     becauſe
    -0.53
     fince
    -0.53
    POSITIVE LOGITS
    IsContent
    0.64
     kasarigan
    0.61
    JspWriter
    0.60
    IUrlHelper
    0.60
     autorytatywna
    0.56
     createState
    0.55
    InitVars
    0.53
     resourceCulture
    0.53
     matter
    0.50
     mater
    0.48
    Activations Density 0.023%

    No Known Activations