© 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. 5-CLT-HP
    4. 1950
    Prev
    Next
    INDEX
    Explanations

    reporting findings

    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
     below
    -0.56
     tranquillo
    -0.50
     abaixo
    -0.50
     obicei
    -0.49
     stří
    -0.49
     européennes
    -0.47
     étrangères
    -0.47
     dieux
    -0.46
    below
    -0.45
     längre
    -0.45
    POSITIVE LOGITS
    InjectAttribute
    0.87
    )");
    
    0.73
    UnusedPrivate
    0.73
    (!__
    0.71
    \{\\
    0.71
    endphp
    0.70
    )";
    
    0.69
    ).}
    0.68
    '],
    
    0.68
    ')")
    0.67
    Activations Density 0.020%

    No Known Activations