© 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. 94563
    Prev
    Next
    INDEX
    Explanations

    suffer/distract

    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
     suffer
    -1.49
     suffers
    -1.49
     suffered
    -1.30
     Suffer
    -1.13
     suffering
    -1.09
     Suffering
    -1.07
    suffering
    -1.05
    __':
    -1.01
     sufferings
    -0.91
     sufri
    -0.88
    POSITIVE LOGITS
     from
    0.78
    red
    0.53
    from
    0.50
    に応じて
    0.50
    ways
    0.49
     FROM
    0.49
    inum
    0.49
    iap
    0.49
     a
    0.48
     */
    0.48
    Activations Density 1.258%

    No Known Activations