© 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. 1-CLT-HP
    7. 15995
    Prev
    Next
    INDEX
    Explanations

    astrology

    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
    expandindo
    -0.69
     menj
    -0.61
    WithMany
    -0.60
     handleMessage
    -0.58
     مرئيه
    -0.58
    uchy
    -0.57
    UnsafeEnabled
    -0.55
     universitaire
    -0.55
    وبه
    -0.55
    AccessException
    -0.55
    POSITIVE LOGITS
     indisponible
    0.62
     ffilmiau
    0.51
    ViewFeatures
    0.49
    AndEndTag
    0.48
    toPromise
    0.47
     XG
    0.46
    GLFW
    0.43
    mogat
    0.43
    PreferredItem
    0.43
    getItemId
    0.42
    Activations Density 0.017%

    No Known Activations