© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15743
    Prev
    Next
    INDEX
    Explanations

    finance

    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
     McKay
    -0.88
    แป
    -0.56
    writerow
    -0.55
    hit
    -0.54
    İstinadlar
    -0.54
     Wikispecies
    -0.50
    perk
    -0.49
    ยนต์
    -0.48
     member
    -0.47
    plish
    -0.45
    POSITIVE LOGITS
    ItemBackground
    0.71
     Curs
    0.66
     Signalez
    0.63
    tagHelperRunner
    0.63
    gdx
    0.62
    UserScript
    0.61
    EndProject
    0.58
    @__
    0.58
    TypedDataSet
    0.58
    ęż
    0.57
    Activations Density 0.017%

    No Known Activations