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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73942
    Prev
    Next
    INDEX
    Explanations

    Technical academic text

    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
    +#+#
    -0.70
    saraba
    -0.59
     Language
    -0.59
    TintMode
    -0.57
    Портал
    -0.56
    хьтан
    -0.55
    談社
    -0.55
     LING
    -0.55
    
    -0.54
     незавершена
    -0.53
    POSITIVE LOGITS
    ]--;
    0.54
    ]),
    
    0.49
    batore
    0.49
    NewUrlParser
    0.48
    ècie
    0.44
    ioutil
    0.44
    viewPager
    0.44
    시오
    0.42
    iNdEx
    0.42
    toMatchSnapshot
    0.41
    Activations Density 0.001%

    No Known Activations