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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 30
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    GraphicsUnit
    -0.84
    ISupport
    -0.68
    StoryboardSegue
    -0.66
     ProtoMessage
    -0.63
     onCreateView
    -0.63
    ReusableCell
    -0.62
    WebServlet
    -0.57
    PerformLayout
    -0.57
     ModelExpression
    -0.57
     חיצוניים
    -0.57
    POSITIVE LOGITS
    hake
    0.60
    ochet
    0.57
     industriels
    0.51
    versiti
    0.50
    racha
    0.50
    entador
    0.50
     lezioni
    0.49
     CHINA
    0.48
     énergé
    0.48
    fă
    0.48
    Activations Density 0.069%

    No Known Activations