© 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. 38
    Prev
    Next
    INDEX
    Explanations

    City names

    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
     indirectly
    -0.54
     holding
    -0.51
     under
    -0.51
     included
    -0.50
     not
    -0.50
     as
    -0.49
     known
    -0.49
     over
    -0.49
     going
    -0.48
     exceeding
    -0.47
    POSITIVE LOGITS
     ExecuteAsync
    0.81
    GEBURTSDATUM
    0.76
     الحره
    0.70
    saraba
    0.70
    \{\\
    0.66
    ंदीखरीदारी
    0.64
    Xna
    0.63
    KommentareTeilen
    0.63
     bakgrund
    0.63
    InSection
    0.59
    Activations Density 0.026%

    No Known Activations