© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93039
    Prev
    Next
    INDEX
    Explanations

    non-local

    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
    remote
    -1.15
    local
    -1.06
     local
    -1.03
     remote
    -1.01
     foreign
    -0.99
    foreign
    -0.99
    Remote
    -0.93
    Local
    -0.90
    external
    -0.90
     exportación
    -0.83
    POSITIVE LOGITS
    ization
    1.13
    ized
    1.11
    izing
    1.06
    izations
    1.04
     Majefty
    1.02
     itſelf
    0.98
     myſelf
    0.96
    izable
    0.93
     Monfieur
    0.93
     Houſe
    0.93
    Activations Density 0.307%

    No Known Activations