© 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. 4-CLT-HP
    7. 3459
    Prev
    Next
    INDEX
    Explanations

    Uncertainty/negation

    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
     typically
    -0.61
    Биография
    -0.61
    なんですが
    -0.58
    Typically
    -0.56
    Abstract
    -0.56
     genellikle
    -0.53
    enangan
    -0.52
     exclusively
    -0.52
     Typically
    -0.52
     either
    -0.50
    POSITIVE LOGITS
    StoryboardSegue
    0.89
     unknownFields
    0.82
    parsedMessage
    0.82
    AddTagHelper
    0.76
    argout
    0.75
    RectangleBorder
    0.74
     nonUne
    0.74
    SharedDtor
    0.73
    IndentedString
    0.73
    AsUp
    0.72
    Activations Density 0.059%

    No Known Activations