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. 12
    Prev
    Next
    INDEX
    Explanations

    biology/enzymes

    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
    ン
    -0.61
    을
    -0.48
    은
    -0.46
     ar
    -0.45
    й
    -0.45
    ів
    -0.43
    ers
    -0.42
    ный
    -0.41
    них
    -0.41
    nois
    -0.40
    POSITIVE LOGITS
     Houſe
    0.83
     Monfieur
    0.83
     Diſ
    0.82
     ſche
    0.81
     myſelf
    0.79
     purpoſe
    0.78
     raiſ
    0.78
     виправивши
    0.77
     uſe
    0.77
     pleaſure
    0.77
    Activations Density 0.102%

    No Known Activations