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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40562
    Prev
    Next
    INDEX
    Explanations

    cancer or infection

    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
    ArrowToggle
    -0.72
     CreateTagHelper
    -0.71
    tagHelperRunner
    -0.69
     démission
    -0.69
     noDo
    -0.67
     étrangers
    -0.67
    verwijspagina
    -0.64
     figliu
    -0.64
     indietro
    -0.63
     colgantes
    -0.63
    POSITIVE LOGITS
     vertical
    0.58
    thood
    0.56
    COUVER
    0.56
    ngx
    0.55
    원
    0.54
    ditionally
    0.53
     people
    0.50
    jwa
    0.49
     ama
    0.49
     baz
    0.48
    Activations Density 0.368%

    No Known Activations