© 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. 46211
    Prev
    Next
    INDEX
    Explanations

    names/locations/medications

    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
     ujednoznacz
    -0.79
    DoubleQuotes
    -0.73
     Joan
    -0.72
    Joan
    -0.70
     Antony
    -0.69
    ing
    -0.68
    ings
    -0.58
    ING
    -0.58
    taan
    -0.53
    Antony
    -0.53
    POSITIVE LOGITS
     itſelf
    0.81
     Efq
    0.79
     myſelf
    0.67
    bukkit
    0.67
     himſelf
    0.67
     Monfieur
    0.66
     ſte
    0.63
     poffe
    0.59
     Shakspeare
    0.59
     ſeveral
    0.57
    Activations Density 0.017%

    No Known Activations