© 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. 96259
    Prev
    Next
    INDEX
    Explanations

    negativity

    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
    AccessorTable
    -0.59
     Threatened
    -0.55
    awtextra
    -0.54
     propOrder
    -0.54
     threatening
    -0.53
     threatened
    -0.53
    ised
    -0.53
    unnitel
    -0.52
    Искәрмәләр
    -0.51
    VIAF
    -0.51
    POSITIVE LOGITS
     препратки
    0.59
    stateProvider
    0.54
     if
    0.53
     pantaloni
    0.52
     anything
    0.52
    enumi
    0.52
    mandu
    0.52
    forName
    0.51
     dieux
    0.50
    if
    0.49
    Activations Density 0.090%

    No Known Activations