© 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. 42987
    Prev
    Next
    INDEX
    Explanations

    observation/possession

    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
     observe
    -2.30
     observed
    -2.27
     observation
    -2.20
     observing
    -2.00
     Observe
    -1.97
     observes
    -1.96
    observed
    -1.96
     Observed
    -1.91
     observations
    -1.84
    observe
    -1.74
    POSITIVE LOGITS
     a
    0.63
     the
    0.63
    ándalo
    0.45
    tagext
    0.43
     an
    0.42
     what
    0.41
     finan
    0.41
     all
    0.40
    RenderAtEndOf
    0.40
     Schiff
    0.40
    Activations Density 0.799%

    No Known Activations