© 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. 76722
    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
     يتيمه
    -0.84
    contentLoaded
    -0.84
     ModelExpression
    -0.74
     utafitiHapana
    -0.67
    AddTagHelper
    -0.67
    ConstraintMaker
    -0.65
    EDEFAULT
    -0.65
     BoxFit
    -0.63
     ligiloj
    -0.61
     ExecuteAsync
    -0.60
    POSITIVE LOGITS
     Karol
    0.48
    Попис
    0.48
     Yarm
    0.47
     Braid
    0.45
     agric
    0.44
     Maho
    0.44
     Gij
    0.43
     sequence
    0.43
    ://
    0.43
     Lennox
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.