© 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. 94893
    Prev
    Next
    INDEX
    Explanations

    evacuation

    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
     evacuate
    -1.22
     evacuated
    -1.05
     evacu
    -0.99
     evacuation
    -0.98
    elemField
    -0.88
    AsUp
    -0.86
    ok
    -0.82
    rungsseite
    -0.80
    }\]
    -0.79
     ModelExpression
    -0.78
    POSITIVE LOGITS
    ING
    0.65
    ing
    0.61
    ers
    0.59
    ings
    0.55
    ER
    0.51
    unref
    0.50
    endo
    0.49
    est
    0.48
    erea
    0.48
     motion
    0.47
    Activations Density 0.180%

    No Known Activations