Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73406
    Prev
    Next
    INDEX
    Explanations

    "above" in other languages

    np_max-act-logits · 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
    )";
    
    -0.83
    Parcelize
    -0.78
    /*
    -0.73
    RetentionPolicy
    -0.71
     EconPapers
    -0.71
    WebVitals
    -0.69
     vPvB
    -0.68
    )");
    
    -0.68
    )++;
    -0.68
    Ữ
    -0.66
    POSITIVE LOGITS
     above
    2.97
    above
    2.56
    Above
    2.42
     Above
    2.38
     ABOVE
    2.11
     acima
    1.90
    ABOVE
    1.59
     diatas
    1.45
     boven
    1.43
    bove
    1.41
    Activations Density 0.000%

    No Known Activations