© 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. 1-CLT-HP
    7. 9689
    Prev
    Next
    INDEX
    Explanations

    oph

    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
    RenderAtEndOf
    -0.73
    TabStop
    -0.62
    ArrowToggle
    -0.47
    іга
    -0.47
    writeFieldEnd
    -0.46
    جستارهای
    -0.46
    webElementXpaths
    -0.44
    beginPath
    -0.43
    تج
    -0.43
     rendono
    -0.43
    POSITIVE LOGITS
     Jolly
    0.53
     useHistory
    0.53
    maid
    0.52
     proprietor
    0.52
     Wheatley
    0.51
     Entrepreneurs
    0.50
    Maid
    0.50
     entrepreneur
    0.50
    /***/
    0.50
    AndFlush
    0.49
    Activations Density 0.004%

    No Known Activations