© 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. 5-CLT-HP
    7. 6328
    Prev
    Next
    INDEX
    Explanations

    figures

    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
     has
    -0.63
     <<<<<<<<<<<<<<
    -0.62
     includes
    -0.58
     replaced
    -0.54
    IMPORTED
    -0.54
    ,
    -0.54
     spends
    -0.53
     impressed
    -0.52
     contains
    -0.52
     makes
    -0.52
    POSITIVE LOGITS
    RegressionTest
    0.69
     Audiodateien
    0.59
     reaſon
    0.57
    roleum
    0.57
     secours
    0.56
    osit
    0.55
     Theſe
    0.55
    achal
    0.55
     reafon
    0.55
    Nutritional
    0.55
    Activations Density 0.001%

    No Known Activations