© 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. 0-CLT-HP
    7. 38883
    Prev
    Next
    INDEX
    Explanations

    Participants and key figures

    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
     supérieures
    -0.62
     démocr
    -0.56
     collègues
    -0.56
     quidem
    -0.56
     leçon
    -0.55
     civiles
    -0.55
     "")
    -0.55
     quæ
    -0.53
    entraînement
    -0.53
     otomatig
    -0.53
    POSITIVE LOGITS
     IConfiguration
    0.73
    GraphicsUnit
    0.67
    PINES
    0.63
     FetchType
    0.58
    angor
    0.55
    RectangleBorder
    0.55
     CascadeType
    0.54
    tagHelperRunner
    0.54
    splitlines
    0.54
    日閲覧
    0.53
    Activations Density 0.017%

    No Known Activations