© 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. 97455
    Prev
    Next
    INDEX
    Explanations

    's

    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
    webElementXpaths
    -0.68
    HasForeignKey
    -0.57
    ApiModelProperty
    -0.56
    Geplaatst
    -0.54
    неопр
    -0.49
     dAtA
    -0.49
    Portail
    -0.49
     createSprite
    -0.48
    JsonFormat
    -0.48
    istia
    -0.48
    POSITIVE LOGITS
    localctx
    0.70
     wikipagina
    0.57
    Tembelea
    0.56
     globally
    0.54
    Heath
    0.52
    woli
    0.52
     aze
    0.52
     ugy
    0.51
     שוליים
    0.51
     Guys
    0.50
    Activations Density 1.629%

    No Known Activations