© 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. 73492
    Prev
    Next
    INDEX
    Explanations

    means and averages

    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
    AndEndTag
    -0.86
    protoimpl
    -0.84
     typelib
    -0.83
     Taktlose
    -0.80
    EndInit
    -0.80
    EndGlobalSection
    -0.79
    :✨
    -0.77
    PerformLayout
    -0.77
    WireFormatLite
    -0.77
    HasForeignKey
    -0.76
    POSITIVE LOGITS
     means
    0.72
     ari
    0.67
     av
    0.67
     geometric
    0.61
     an
    0.59
     arithmetic
    0.57
     avere
    0.54
    几何
    0.54
     ave
    0.54
     arit
    0.49
    Activations Density 0.007%

    No Known Activations