© 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. 1-CLT-HP
    7. 9095
    Prev
    Next
    INDEX
    Explanations

    isolation

    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
     Isolation
    -0.81
    Isolation
    -0.79
     Isol
    -0.74
    Robinson
    -0.72
    isolation
    -0.71
    WindowConstants
    -0.71
     isolation
    -0.65
     Robinson
    -0.64
     leaſt
    -0.62
     greateſt
    -0.61
    POSITIVE LOGITS
     propOrder
    0.50
     peix
    0.48
    ResumeLayout
    0.48
    padu
    0.48
    Paraguay
    0.47
    Hades
    0.45
    xsi
    0.45
    basicConfig
    0.44
     gainera
    0.43
     unknownFields
    0.43
    Activations Density 0.017%

    No Known Activations