© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93307
    Prev
    Next
    INDEX
    Explanations

    academic papers

    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
    WriteTagHelper
    -0.86
     an
    -0.84
     nahilalakip
    -0.76
    OGND
    -0.73
    assemblée
    -0.66
     Seeder
    -0.65
    tagHelperRunner
    -0.64
    extré
    -0.63
     transfieras
    -0.62
     ویکی‌پدی
    -0.61
    POSITIVE LOGITS
     algorithm
    0.65
     array
    0.65
     estimate
    0.61
     average
    0.59
     assortment
    0.56
     infection
    0.56
    tismo
    0.56
     allez
    0.56
     effective
    0.56
     integrated
    0.56
    Activations Density 0.055%

    No Known Activations