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. 74458
    Prev
    Next
    INDEX
    Explanations

    collagen

    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
     propOrder
    -0.73
     &___
    -0.67
    PerformLayout
    -0.66
     ſtate
    -0.66
     houſe
    -0.63
     snippetHide
    -0.63
    featureID
    -0.63
     myſelf
    -0.63
    /***/
    -0.63
     '\\;'
    -0.62
    POSITIVE LOGITS
     G
    0.73
     Allen
    0.71
    G
    0.63
    Allen
    0.57
     g
    0.56
    整
    0.49
    G
    0.48
     al
    0.45
     Allan
    0.44
    g
    0.44
    Activations Density 0.004%

    No Known Activations