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. 20-CLT-HP
    4. 74078
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     goblet
    -0.56
    avelin
    -0.54
    writeField
    -0.51
     shoe
    -0.49
     vases
    -0.49
     bro
    -0.48
     disciplinary
    -0.47
     cleats
    -0.47
     flocc
    -0.47
     glove
    -0.47
    POSITIVE LOGITS
    ]")]
    0.69
    mybatisplus
    0.59
     indisponible
    0.57
    NUMX
    0.54
    UserScript
    0.51
    ())));
    0.50
     مشين
    0.50
     joaat
    0.50
    +#+#
    0.49
     NOI
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.