© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1102
    Prev
    Next
    INDEX
    Explanations

    Code/programming snippets

    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
     financières
    -0.65
     choisissez
    -0.58
     enfans
    -0.56
     exitos
    -0.56
     publiques
    -0.54
     militaires
    -0.53
     âmes
    -0.53
     sœurs
    -0.53
     lunak
    -0.52
     éner
    -0.52
    POSITIVE LOGITS
    expandindo
    0.64
    SourceChecksum
    0.59
    AddTagHelper
    0.59
    ScopeManager
    0.56
    __(/*!
    0.56
     nahilalakip
    0.54
     the
    0.53
    webElementXpaths
    0.52
    ReusableCell
    0.52
    remel
    0.50
    Activations Density 0.001%

    No Known Activations