© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91525
    Prev
    Next
    INDEX
    Explanations

    countries

    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
     America
    -0.66
    ReusableCell
    -0.65
     ProtoMessage
    -0.61
     nakalista
    -0.60
     US
    -0.59
     amerik
    -0.56
     AMERICA
    -0.56
    bootstrapcdn
    -0.55
     Fre
    -0.55
     USA
    -0.54
    POSITIVE LOGITS
     kiin
    0.63
     censiti
    0.59
    tvguidetime
    0.58
     Nimbus
    0.56
     digitais
    0.55
    ContentAsync
    0.54
    InjectAttribute
    0.51
     untersuchen
    0.50
     Conservatory
    0.50
     larmes
    0.49
    Activations Density 0.001%

    No Known Activations