© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90672
    Prev
    Next
    INDEX
    Explanations

    rett/defin

    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
    rett
    -1.09
     messengers
    -1.03
    twimg
    -0.70
    elancer
    -0.56
    Contrast
    -0.54
     contrast
    -0.53
     padlock
    -0.52
    ecma
    -0.51
     comod
    -0.51
     Contrast
    -0.50
    POSITIVE LOGITS
    FormTagHelper
    0.67
     AssemblyProduct
    0.65
    لينكات
    0.53
     MatDialog
    0.53
    dollis
    0.52
     affari
    0.52
    нительно
    0.51
     AssemblyCompany
    0.50
     NUKAT
    0.50
    unknownFields
    0.49
    Activations Density 0.922%

    No Known Activations