© 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. 95596
    Prev
    Next
    INDEX
    Explanations

    charters and rods

    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
    Walking
    -0.75
     NgModule
    -0.72
    caught
    -0.71
    stood
    -0.69
     שוליים
    -0.67
    moins
    -0.65
    ValueStyle
    -0.65
    Caught
    -0.64
     caught
    -0.64
    structors
    -0.64
    POSITIVE LOGITS
    queryInterface
    0.49
    例文帳に追加
    0.48
     stretch
    0.44
     Würzburg
    0.44
    ']))
    0.42
     Damit
    0.42
     Bew
    0.42
     pernicious
    0.42
     twist
    0.40
     escalate
    0.40
    Activations Density 0.556%

    No Known Activations