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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74575
    Prev
    Next
    INDEX
    Explanations

    Code and foreign 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
     StringTokenizer
    -0.54
     蓝
    -0.54
     Ngày
    -0.53
     Nước
    -0.52
     首页
    -0.50
     eyeshadow
    -0.49
     图标
    -0.49
     卡片
    -0.48
     cookware
    -0.48
     下午
    -0.48
    POSITIVE LOGITS
    __);
    0.61
    ]<<"
    0.59
    ]))
    
    0.58
    })),
    0.54
    })]
    0.53
    __))
    0.51
    __)
    0.50
    })).
    0.48
    '}),
    0.48
    })));
    0.48
    Activations Density 0.093%

    No Known Activations