© 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. 95784
    Prev
    Next
    INDEX
    Explanations

    dementia

    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
     dementia
    -0.90
     memorial
    -0.66
     wikipagina
    -0.65
    intérêt
    -0.58
     rapides
    -0.57
     poussière
    -0.55
     retirement
    -0.55
     fumée
    -0.52
    inan
    -0.51
    memorial
    -0.51
    POSITIVE LOGITS
    ization
    0.77
    etheless
    0.73
    sterious
    0.69
    izing
    0.68
     Paglinawan
    0.65
    ized
    0.64
    theless
    0.64
     "));
    0.62
    "])
    0.62
     kaarangay
    0.61
    Activations Density 0.091%

    No Known Activations