© 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. 4492
    Prev
    Next
    INDEX
    Explanations

    leaving

    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
     <>",
    -0.45
     Lordships
    -0.45
    SequentialGroup
    -0.44
    playa
    -0.43
     bew
    -0.43
    PerformLayout
    -0.43
     mexican
    -0.41
     Réponses
    -0.41
     RoutedEventArgs
    -0.41
     angler
    -0.41
    POSITIVE LOGITS
     his
    0.63
     home
    0.59
    ValueStyle
    0.57
     erfaren
    0.54
     jspb
    0.53
     służ
    0.51
     colleagues
    0.50
    IMPORTED
    0.50
    ctivité
    0.50
    reuth
    0.49
    Activations Density 0.002%

    No Known Activations