© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91911
    Prev
    Next
    INDEX
    Explanations

    Engines, metals, and decades

    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
     enfans
    -0.93
     démocr
    -0.91
     cuivre
    -0.90
    findpost
    -0.88
    IntoConstraints
    -0.88
     colère
    -0.88
     avoient
    -0.88
     nôtre
    -0.88
     chré
    -0.87
     myſelf
    -0.87
    POSITIVE LOGITS
    i
    0.71
     
    0.71
    e
    0.69
    ed
    0.69
    ization
    0.64
    a
    0.64
    s
    0.60
    1
    0.59
    ized
    0.57
     feedback
    0.56
    Activations Density 0.091%

    No Known Activations