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. 74063
    Prev
    Next
    INDEX
    Explanations

    public

    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
    MessageOf
    -0.79
    ViewFeatures
    -0.74
    cshtml
    -0.66
    TagHelper
    -0.64
     continúas
    -0.60
    PreferredItem
    -0.58
     lenker
    -0.58
    клопе
    -0.57
    elemField
    -0.57
     تضيفلها
    -0.57
    POSITIVE LOGITS
     end
    0.57
     Вікіпе
    0.57
    OptionsMenu
    0.51
    uxxxx
    0.51
     leave
    0.50
     press
    0.50
     access
    0.47
     Obtenez
    0.46
     ends
    0.45
    UnsafeEnabled
    0.45
    Activations Density 0.000%

    No Known Activations