© 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. 76492
    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
    IVEREF
    -0.70
    AntiForgeryToken
    -0.65
    gonic
    -0.59
    fromnode
    -0.58
    rungsseite
    -0.58
    rancy
    -0.57
    ollectionView
    -0.56
    HostException
    -0.56
    OSIS
    -0.55
    |}{
    -0.53
    POSITIVE LOGITS
    ométrique
    0.52
     inflater
    0.50
    ceries
    0.50
     समीक्षाओं
    0.50
     MessageBox
    0.49
    bash
    0.47
    Smarty
    0.46
    awtextra
    0.45
    initializeApp
    0.45
     PHR
    0.45
    Activations Density 0.004%

    No Known Activations