Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74410
    Prev
    Next
    INDEX
    Explanations

    scientific research and genes

    np_max-act-logits · 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
     épaules
    -0.56
    Soorten
    -0.48
     morrer
    -0.48
     sudut
    -0.48
     Agency
    -0.48
     offent
    -0.47
     kelebihan
    -0.47
     Info
    -0.46
     necessariamente
    -0.46
     alapján
    -0.45
    POSITIVE LOGITS
    yntaxException
    0.72
    ElementException
    0.65
     acting
    0.65
    AnchorStyles
    0.59
    parsedMessage
    0.59
    Acting
    0.57
     active
    0.57
    xase
    0.55
    PMailer
    0.54
     expresses
    0.54
    Activations Density 0.010%

    No Known Activations