© 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. 20-CLT-HP
    7. 72672
    Prev
    Next
    INDEX
    Explanations

    studies and measurements

    np_max-act-logits · 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
    lying
    -0.61
    ysing
    -0.59
     disclosing
    -0.59
    cing
    -0.57
     disseminating
    -0.56
    calling
    -0.56
    going
    -0.55
    lizing
    -0.55
     paying
    -0.54
     confirming
    -0.54
    POSITIVE LOGITS
     Majefty
    0.60
     Joined
    0.60
     Studied
    0.58
    studied
    0.58
     Measured
    0.57
     studied
    0.56
    adaptiveStyles
    0.56
    AILED
    0.56
     houſe
    0.56
     measured
    0.56
    Activations Density 0.002%

    No Known Activations