© 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. 6097
    Prev
    Next
    INDEX
    Explanations

    prime

    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
    tagHelperRunner
    -0.57
    ienka
    -0.56
     vulgaires
    -0.56
    CloseOperation
    -0.55
    uesia
    -0.54
     فريبيس
    -0.52
     estimés
    -0.52
    izophrenia
    -0.50
    richTextPanel
    -0.50
    ness
    -0.50
    POSITIVE LOGITS
    val
    0.65
     rib
    0.63
    forward
    0.57
    irc
    0.54
    rib
    0.54
     propOrder
    0.51
    al
    0.51
    umbai
    0.51
    ally
    0.50
    time
    0.50
    Activations Density 0.004%

    No Known Activations