© 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. 44218
    Prev
    Next
    INDEX
    Explanations

    government positions

    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
     ag
    -0.56
     as
    -0.52
     working
    -0.43
     today
    -0.42
     having
    -0.42
     down
    -0.42
     in
    -0.41
     another
    -0.41
    .
    -0.40
     beginning
    -0.40
    POSITIVE LOGITS
    URLException
    0.85
    ftagPool
    0.84
     bezeichneter
    0.82
    __':
    0.80
    UserScript
    0.80
    DrawerToggle
    0.75
    RenderAtEndOf
    0.75
    potranspiration
    0.73
     Meksiku
    0.72
     ModelExpression
    0.72
    Activations Density 0.098%

    No Known Activations