© 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. 12215
    Prev
    Next
    INDEX
    Explanations

    Law, engineering, or science

    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
     justices
    -2.05
     Justices
    -1.74
     surla
    -0.83
    
    -0.81
    Jus
    -0.79
     Jus
    -0.69
    expandindo
    -0.63
    farin
    -0.63
    kháu
    -0.62
     judges
    -0.61
    POSITIVE LOGITS
    Schwer
    0.49
    Personensuche
    0.47
    Heavy
    0.47
     poitrine
    0.47
     barba
    0.45
    Triple
    0.45
    Hands
    0.44
    ánh
    0.44
    Dono
    0.43
    hands
    0.43
    Activations Density 0.013%

    No Known Activations