© 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. 42428
    Prev
    Next
    INDEX
    Explanations

    observation

    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
    -1.67
     observations
    -1.45
     observ
    -1.19
     observing
    -1.16
    observation
    -1.16
     observed
    -1.09
     Observation
    -1.02
     observes
    -1.02
     obser
    -1.00
     observe
    -0.99
    POSITIVE LOGITS
     propOrder
    0.96
    出版年
    0.81
    addPreferredGap
    0.80
    thâu
    0.78
     <>",
    0.78
     <=",
    0.76
     raiſ
    0.75
    mbolos
    0.74
     שוליים
    0.72
     Roskov
    0.71
    Activations Density 0.039%

    No Known Activations