© 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. 94358
    Prev
    Next
    INDEX
    Explanations

    Code/URLs

    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
     autorytatywna
    -0.78
     فريبيس
    -0.68
    migrationBuilder
    -0.65
     betweenstory
    -0.59
     continúas
    -0.59
     propOrder
    -0.56
    +#+#
    -0.55
     CreateTagHelper
    -0.52
    :✨
    -0.51
    modelBuilder
    -0.51
    POSITIVE LOGITS
    ">'.$
    0.59
    })()
    0.59
    헌
    0.58
    Via
    0.52
    FontOfSize
    0.52
     méta
    0.51
     légitime
    0.50
     مؤرشف
    0.50
     heureux
    0.50
     wijze
    0.49
    Activations Density 0.100%

    No Known Activations