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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73711
    Prev
    Next
    INDEX
    Explanations

    many

    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
    tably
    -0.68
     calldata
    -0.67
    soever
    -0.63
    τία
    -0.62
    Искәрмәләр
    -0.61
    AccessorTable
    -0.61
    Бахар
    -0.61
    IndentedString
    -0.57
     оригіналу
    -0.57
    teness
    -0.56
    POSITIVE LOGITS
     thousands
    0.65
     moons
    0.65
     more
    0.64
     millions
    0.61
     thanks
    0.57
    Дере
    0.53
    hyrchwyd
    0.52
     hundreds
    0.51
    thousands
    0.50
     περισσότε
    0.49
    Activations Density 0.040%

    No Known Activations