© 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. 1-CLT-HP
    7. 12327
    Prev
    Next
    INDEX
    Explanations

    news/politics

    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
    findpost
    -0.68
    tagHelperRunner
    -0.61
    ParallelGroup
    -0.59
    enumii
    -0.58
    istoitu
    -0.57
     Савезне
    -0.54
     CreateTagHelper
    -0.53
    endregion
    -0.52
    ñores
    -0.51
    WebMethod
    -0.50
    POSITIVE LOGITS
     intptr
    0.73
    __':
    0.63
     StatelessWidget
    0.59
    yanka
    0.57
    momix
    0.55
     StatefulWidget
    0.54
     Kitch
    0.54
    __":
    0.52
    anskje
    0.51
    üyada
    0.50
    Activations Density 0.022%

    No Known Activations