© 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. 5-CLT-HP
    7. 94822
    Prev
    Next
    INDEX
    Explanations

    main subject

    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
    contentLoaded
    -0.62
    NameInMap
    -0.58
    ValueStyle
    -0.55
     Numerade
    -0.55
     الحره
    -0.54
    Демографія
    -0.54
    Према
    -0.54
     مرئيه
    -0.51
    '
    -0.50
    GEBURTSDATUM
    -0.50
    POSITIVE LOGITS
    hdashline
    0.51
    verifyException
    0.51
     tratto
    0.48
     compito
    0.45
     sekal
    0.45
     newOwner
    0.44
     kampen
    0.44
    jooq
    0.44
     task
    0.44
     tratti
    0.43
    Activations Density 0.011%

    No Known Activations