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. 0-CLT-HP
    4. 14
    Prev
    Next
    INDEX
    Explanations

    injuries

    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
    ParallelGroup
    -0.75
    脚注の使い方
    -0.68
    
    -0.68
     autorytatywna
    -0.66
     صوتيه
    -0.66
     للاسماء
    -0.65
    )$}
    -0.64
    SequentialGroup
    -0.63
    TagHelper
    -0.62
     CreateTagHelper
    -0.62
    POSITIVE LOGITS
    #+#
    0.57
     secretions
    0.56
     atof
    0.56
     africana
    0.53
     hemispheres
    0.51
     aryl
    0.50
     polypropylene
    0.49
     hemisphere
    0.48
     salivary
    0.48
     epithe
    0.48
    Activations Density 0.432%

    No Known Activations