© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78223
    Prev
    Next
    INDEX
    Explanations

    Los Angeles or Las Vegas

    np_max-act-logits · 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
    Negative Logits
    TProtocol
    -0.59
    tdc
    -0.58
    MergeFrom
    -0.56
     Partagez
    -0.53
     Set
    -0.52
    iteur
    -0.52
    LOV
    -0.52
     K
    -0.51
     Takeaway
    -0.51
    angliski
    -0.51
    POSITIVE LOGITS
    Personensuche
    0.83
    MemoryWarning
    0.74
    AnchorStyles
    0.61
    tagHelperRunner
    0.57
     ModelExpression
    0.55
     nôtre
    0.52
     Altos
    0.48
     secondaire
    0.48
    Parcelize
    0.47
    KommentareTeilen
    0.47
    Activations Density 0.005%

    No Known Activations