© 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. 4-CLT-HP
    7. 342
    Prev
    Next
    INDEX
    Explanations

    technical processes

    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
    verwijspagina
    -0.75
    曖昧さ回避
    -0.69
     CreateTagHelper
    -0.67
    AsUp
    -0.67
     تضيفلها
    -0.65
    ThroughAttribute
    -0.63
     kasarigan
    -0.59
    awtextra
    -0.59
    antMatchers
    -0.58
    WriteTagHelper
    -0.57
    POSITIVE LOGITS
     the
    0.88
     it
    0.77
    KommentareTeilen
    0.56
    IonicModule
    0.53
    slidesToShow
    0.48
     Sekret
    0.47
     a
    0.46
    uesia
    0.45
    וויק
    0.43
    り返
    0.43
    Activations Density 0.003%

    No Known Activations