© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95410
    Prev
    Next
    INDEX
    Explanations

    practical/practice

    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
    Practical
    -1.02
    practical
    -1.02
     practical
    -0.98
     Practical
    -0.91
    Practice
    -0.90
     PRACTICAL
    -0.86
     Practice
    -0.85
     pratique
    -0.81
    practice
    -0.76
    Practi
    -0.75
    POSITIVE LOGITS
    ReusableCell
    1.03
    SharedCtor
    1.02
    MigrationBuilder
    0.91
    AndEndTag
    0.90
    SharedDtor
    0.88
     referenties
    0.87
     nakalista
    0.86
     propOrder
    0.86
     ſeveral
    0.84
    AnchorStyles
    0.83
    Activations Density 0.072%

    No Known Activations