© 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. 95628
    Prev
    Next
    INDEX
    Explanations

    government, official, dates

    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
    Negative Logits
     significantly
    -0.83
     particularly
    -0.82
     Mo
    -0.73
     significant
    -0.65
    est
    -0.63
    Mo
    -0.60
     particularmente
    -0.60
    particularly
    -0.57
     "
    -0.50
     August
    -0.50
    POSITIVE LOGITS
    RegistryLite
    1.14
     itſelf
    1.08
     propOrder
    1.05
    EDEFAULT
    1.00
     myſelf
    0.98
    AndEndTag
    0.96
     Efq
    0.92
    abestanden
    0.91
    PerformLayout
    0.91
     raiſ
    0.91
    Activations Density 0.176%

    No Known Activations