Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74226
    Prev
    Next
    INDEX
    Explanations

    News snippets

    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
     Superhost
    -0.57
     bitten
    -0.53
    ViewChild
    -0.51
     CreateTagHelper
    -0.51
     gants
    -0.50
     Houſe
    -0.50
    grine
    -0.49
    IMPORTED
    -0.48
     Superhosts
    -0.48
     Koy
    -0.48
    POSITIVE LOGITS
    ⓧ
    0.71
    broek
    0.58
    ÁB
    0.54
    INSEE
    0.52
    Спољашње
    0.51
     Ex
    0.51
     otomatig
    0.50
     ray
    0.50
    RTHOOK
    0.50
     Réponses
    0.50
    Activations Density 0.000%

    No Known Activations