© 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. 77087
    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
    AddTagHelper
    -0.89
     kaarangay
    -0.86
    Personendaten
    -0.82
     Normdatei
    -0.77
    GOTREF
    -0.77
    elemField
    -0.76
     viewType
    -0.75
    principalTable
    -0.74
    ModelSerializer
    -0.73
    MLLoader
    -0.72
    POSITIVE LOGITS
     the
    0.87
     typically
    0.71
     ones
    0.50
    typically
    0.49
     probably
    0.49
    probably
    0.47
     Typically
    0.47
     vôtre
    0.47
     your
    0.44
     among
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.