© 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. 1-CLT-HP
    7. 11354
    Prev
    Next
    INDEX
    Explanations

    organizations and locations

    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
     Gerais
    -0.69
     econômica
    -0.66
     coö
    -0.66
     kasarigan
    -0.65
    NUMX
    -0.64
     picioare
    -0.64
     acá
    -0.63
     يتيمه
    -0.62
    MENAFN
    -0.61
    australia
    -0.61
    POSITIVE LOGITS
     AssemblyCompany
    0.62
     ujednoznacz
    0.47
    RunAsync
    0.47
    gebir
    0.46
    ---*/
    0.44
    tili
    0.43
    .
    0.42
    ija
    0.40
    ése
    0.40
    pley
    0.40
    Activations Density 0.013%

    No Known Activations