© 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. 91070
    Prev
    Next
    INDEX
    Explanations

    may

    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
     resourceCulture
    -0.52
     Open
    -0.51
     yourself
    -0.49
    geführt
    -0.48
    prav
    -0.47
     pair
    -0.47
     Advanced
    -0.46
    pasan
    -0.45
    もの
    -0.45
    tät
    -0.45
    POSITIVE LOGITS
    Personensuche
    0.78
     فريبيس
    0.72
    UnsafeEnabled
    0.70
    both
    0.65
     gddr
    0.61
    ütün
    0.60
    Both
    0.60
     allemaal
    0.60
    Diwedd
    0.59
    Становништво
    0.57
    Activations Density 0.001%

    No Known Activations