© 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. 1-CLT-HP
    7. 13477
    Prev
    Next
    INDEX
    Explanations

    ano

    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
     Kla
    -0.53
     kla
    -0.53
    kla
    -0.48
     Pik
    -0.47
     Sew
    -0.47
     Province
    -0.46
    SAM
    -0.46
     Thousand
    -0.45
    deler
    -0.45
    dela
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.82
    IntoConstraints
    0.77
    Izvori
    0.75
     AssemblyCompany
    0.71
    Erreferentziak
    0.69
    Autoritní
    0.69
    ValueStyle
    0.69
    verwijspagina
    0.68
    Diweddarwch
    0.68
    ContentAsync
    0.67
    Activations Density 0.019%

    No Known Activations