© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5602
    Prev
    Next
    INDEX
    Explanations

    illness and disease

    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
    Not in Any Lists

    No Comments

    Negative Logits
     need
    -0.55
     damage
    -0.53
     affects
    -0.53
     bad
    -0.51
     blow
    -0.50
     Mal
    -0.49
    TagHelpers
    -0.48
    ewon
    -0.47
     worst
    -0.47
     effects
    -0.46
    POSITIVE LOGITS
    DockStyle
    0.97
     виправивши
    0.84
    GEBURTSDATUM
    0.84
     Paglinawan
    0.82
     विश्वसनीयता
    0.81
     referenties
    0.78
    queryInterface
    0.75
    ArgsConstructor
    0.75
     CreateTagHelper
    0.73
     bezeichneter
    0.73
    Activations Density 0.002%

    No Known Activations