© 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. 91990
    Prev
    Next
    INDEX
    Explanations

    closures, legal matters, copyright

    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
     BorderRadius
    -0.77
    LabelTagHelper
    -0.70
    Diweddarwch
    -0.69
     nî
    -0.68
    fillType
    -0.68
    criminator
    -0.65
     }}"></
    -0.65
    CodedInputStream
    -0.63
     ModelRenderer
    -0.61
    TagHelper
    -0.60
    POSITIVE LOGITS
     renovations
    0.64
     renovation
    0.61
     improvement
    0.60
     improvements
    0.58
    Renov
    0.58
     perbaikan
    0.57
     refurb
    0.57
     redesign
    0.56
     revamp
    0.55
     reform
    0.53
    Activations Density 0.001%

    No Known Activations