© 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. 77835
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tvguidetime
    -0.71
     newBuilder
    -0.71
    +#+#
    -0.68
    IUrlHelper
    -0.67
     Benth
    -0.66
     Wikimedijinoj
    -0.65
    ourites
    -0.64
    strato
    -0.64
    kháu
    -0.63
    errit
    -0.62
    POSITIVE LOGITS
     sensitive
    0.39
     sensitivity
    0.38
    sensitivity
    0.38
    ]=='
    0.36
    ]!='
    0.36
    Sensitive
    0.35
    SENS
    0.34
     Sunak
    0.33
    ]=="
    0.32
     Sensitivity
    0.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.