© 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. 408
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
     faſt
    -0.68
    ValueStyle
    -0.66
     uſe
    -0.66
     ſeveral
    -0.61
    neſs
    -0.60
     purpoſe
    -0.60
     reafon
    -0.57
     firſt
    -0.57
     reaſon
    -0.57
    +#+#
    -0.57
    POSITIVE LOGITS
     externi
    0.55
    trina
    0.50
     Resorts
    0.49
     GridLayout
    0.48
     стри
    0.47
    XmlIgnore
    0.46
    Lähteet
    0.46
    Välislingid
    0.45
     дописавши
    0.45
     Cuts
    0.45
    Activations Density 0.009%

    No Known Activations