© 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. 809
    Prev
    Next
    INDEX
    Explanations

    t

    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
     defaultstate
    -0.82
    ScopeManager
    -0.58
    partum
    -0.57
     itſelf
    -0.55
     LoggerFactory
    -0.54
     Josephus
    -0.54
     ſp
    -0.54
    uttavia
    -0.53
     ſte
    -0.53
     minors
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    0.65
     дописавши
    0.62
     بتوان
    0.54
    OGND
    0.53
    قایناق‌لار
    0.51
    Datuak
    0.50
    GEBURTS
    0.50
     قاد
    0.50
     Meksiku
    0.49
     OFDb
    0.49
    Activations Density 0.002%

    No Known Activations