© 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. 0-CLT-HP
    7. 38848
    Prev
    Next
    INDEX
    Explanations

    соб

    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
     Référence
    -0.88
    SourceChecksum
    -0.86
    PerformLayout
    -0.79
     للاسماء
    -0.79
     jScrollPane
    -0.77
    HideFlags
    -0.75
     EconPapers
    -0.65
    abestanden
    -0.64
    IndentedString
    -0.64
    ///</
    -0.63
    POSITIVE LOGITS
    alignSelf
    0.53
    istisches
    0.52
     tanam
    0.50
    medim
    0.48
     stessi
    0.47
    PRNewswire
    0.47
     inond
    0.47
     mattina
    0.45
     vitt
    0.45
     Zust
    0.45
    Activations Density 0.902%

    No Known Activations