© 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. 5-CLT-HP
    7. 98212
    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
     tartalomajánló
    -0.61
    IBOutlet
    -0.49
     XCTest
    -0.46
     NUnit
    -0.44
    vician
    -0.44
    softc
    -0.43
     nahilalakip
    -0.42
    cotte
    -0.41
    Jegyzetek
    -0.41
    msgTypes
    -0.41
    POSITIVE LOGITS
     nawr
    0.64
     متعلقه
    0.56
    uría
    0.54
    elemField
    0.53
    AndroidJUnit
    0.52
    awtextra
    0.52
    CrossRef
    0.51
     sobretudo
    0.47
     FBref
    0.47
    DeleteBehavior
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.