© 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. 0-CLT-HP
    7. 95063
    Prev
    Next
    INDEX
    Explanations

    cities/locations

    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
     Lincoln
    -0.77
    Lincoln
    -0.70
     Phoenix
    -0.61
    Phoenix
    -0.59
     Madison
    -0.56
    phoenix
    -0.52
    Madison
    -0.48
     ber
    -0.42
     bort
    -0.42
     lincoln
    -0.41
    POSITIVE LOGITS
     HasFactory
    1.19
     Majefty
    1.16
     Jefus
    1.15
     Monfieur
    1.08
     itſelf
    1.07
    expandindo
    1.04
     myſelf
    1.04
     Houſe
    1.03
    TagMode
    1.02
    ]--;
    1.02
    Activations Density 1.133%

    No Known Activations