© 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. 72144
    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
    Was
    -0.80
    tanleria
    -0.76
    was
    -0.75
    “
    -0.74
     >=",
    -0.67
    astify
    -0.64
    wasn
    -0.64
     Was
    -0.63
    例文帳に追加
    -0.62
    “-
    -0.61
    POSITIVE LOGITS
     are
    0.99
     effecting
    0.60
     loosing
    0.55
     loose
    0.54
     effects
    0.51
     praying
    0.50
     sending
    0.49
     crushing
    0.49
     executing
    0.49
     acting
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.