© 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. 72201
    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
    IUrlHelper
    -0.85
    oredCriteria
    -0.83
    parsedMessage
    -0.81
    NOPQRST
    -0.81
    HideFlags
    -0.78
     indisponible
    -0.75
     Савезне
    -0.72
     alman
    -0.70
     tartalomajánló
    -0.70
    ########.
    -0.70
    POSITIVE LOGITS
     maiores
    0.42
     outils
    0.36
    //
    0.35
     provecho
    0.35
     metade
    0.33
     inferiores
    0.32
    Command
    0.31
    waniem
    0.31
    big
    0.30
    Thx
    0.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.