© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1097
    Prev
    Next
    INDEX
    Explanations

    that

    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
     gagné
    -0.59
     autorité
    -0.56
     féminine
    -0.55
     for
    -0.55
    guenos
    -0.53
    ctif
    -0.53
     directiva
    -0.53
     kanan
    -0.52
     right
    -0.52
     vécu
    -0.52
    POSITIVE LOGITS
    :✨
    1.05
    Diwedd
    0.80
     nakalista
    0.79
     disambiguazione
    0.74
    WebElementEntity
    0.68
     Италијани
    0.68
     disponibilités
    0.67
     CreateTagHelper
    0.67
    StoreMessageInfo
    0.63
     betweenstory
    0.62
    Activations Density 0.004%

    No Known Activations