© 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. 10331
    Prev
    Next
    INDEX
    Explanations

    observer

    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
     observation
    -0.94
     observers
    -0.83
     observ
    -0.82
     observer
    -0.82
     osserv
    -0.77
     Observation
    -0.76
     OBSERV
    -0.72
     observations
    -0.71
     observación
    -0.71
     observe
    -0.69
    POSITIVE LOGITS
     Normdatei
    0.87
    MigrationBuilder
    0.83
     useAuth
    0.82
     useRouter
    0.81
     useAppContext
    0.81
     مرئيه
    0.76
    CodedInputStream
    0.75
    autoconfigure
    0.73
     يتيمه
    0.73
     bunting
    0.72
    Activations Density 0.041%

    No Known Activations