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. 0-CLT-HP
    4. 520
    Prev
    Next
    INDEX
    Explanations

    Code/software

    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
    .
    -0.59
    IsRequired
    -0.50
    ypeł
    -0.48
     results
    -0.46
     double
    -0.46
    ypsies
    -0.46
     fat
    -0.45
     inſ
    -0.45
    хео
    -0.45
    raborty
    -0.45
    POSITIVE LOGITS
    )}</
    0.91
     }));
    0.90
    saraba
    0.87
     }))
    0.87
    }))
    
    0.86
     });
    0.85
     });
    
    0.85
     Мексичка
    0.82
    __":
    
    0.82
     }}</
    0.81
    Activations Density 0.312%

    No Known Activations