© 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. 5-CLT-HP
    7. 94337
    Prev
    Next
    INDEX
    Explanations

    groups of people

    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
    MethodManager
    -0.82
     فريبيس
    -0.71
    CppMethod
    -0.71
     propOrder
    -0.70
    joba
    -0.68
    Geplaatst
    -0.67
    ConstraintMaker
    -0.67
     dAtA
    -0.66
     AssemblyCulture
    -0.65
     Вікі
    -0.65
    POSITIVE LOGITS
    väg
    0.48
     présents
    0.46
    nende
    0.45
    okia
    0.44
     úteis
    0.41
     折
    0.41
     precisione
    0.41
     favorables
    0.41
     loisirs
    0.41
     délais
    0.41
    Activations Density 0.002%

    No Known Activations