© 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. 4-CLT-HP
    7. 2500
    Prev
    Next
    INDEX
    Explanations

    actions impacting 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
     son
    -0.42
    inek
    -0.40
     pen
    -0.39
    per
    -0.39
    ceq
    -0.38
    連
    -0.37
     co
    -0.37
     des
    -0.37
     leksikon
    -0.37
    gest
    -0.37
    POSITIVE LOGITS
     виправивши
    0.81
     Audiodateien
    0.73
     myſelf
    0.71
     ujednoznacz
    0.69
     $_"
    0.68
     OFDb
    0.68
    aarrggbb
    0.66
    ⓘ
    0.66
     ModelExpression
    0.66
    atrician
    0.66
    Activations Density 0.004%

    No Known Activations