© 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. 2360
    Prev
    Next
    INDEX
    Explanations

    Instructions or advice

    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
    @[+][
    -0.75
     AssemblyTitle
    -0.65
    httphttps
    -0.63
     people
    -0.63
    PreferredItem
    -0.62
     Efq
    -0.61
     unknownFields
    -0.59
    SharedDtor
    -0.56
    ReusableCell
    -0.55
     jScrollPane
    -0.55
    POSITIVE LOGITS
     évent
    0.67
    will
    0.61
     eventuali
    0.60
     mahdollis
    0.60
     dieux
    0.60
     risques
    0.60
    Might
    0.59
     mahd
    0.58
     mínimos
    0.57
     prochaines
    0.57
    Activations Density 0.002%

    No Known Activations