© 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. 399
    Prev
    Next
    INDEX
    Explanations

    to

    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
     also
    -0.68
     reportedly
    -0.53
     see
    -0.52
     not
    -0.51
     initially
    -0.50
     primarily
    -0.48
     apparently
    -0.48
     briefly
    -0.46
     somehow
    -0.46
     generally
    -0.45
    POSITIVE LOGITS
     armée
    0.73
     disambiguazione
    0.64
    haustible
    0.62
     nôtre
    0.60
     nonatomic
    0.60
     zijne
    0.60
    épendance
    0.59
    soort
    0.59
     artyku
    0.59
     nødven
    0.59
    Activations Density 0.012%

    No Known Activations