© 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. 91848
    Prev
    Next
    INDEX
    Explanations

    most

    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
    jsii
    -0.51
    squareup
    -0.50
    main
    -0.46
    j
    -0.46
    гла
    -0.45
    Main
    -0.45
     principali
    -0.44
     suela
    -0.43
    fml
    -0.43
    to
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.89
     NSCoder
    0.77
    AddTagHelper
    0.76
     attestation
    0.69
     مشين
    0.67
    createCanvas
    0.66
    ']))
    0.63
    WriteTagHelper
    0.60
    SharedCtor
    0.60
     acquittal
    0.58
    Activations Density 0.001%

    No Known Activations