© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 76404
    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
    '])
    
    -0.62
     bluza
    -0.61
     XCTest
    -0.61
    ']));
    -0.61
     "");
    
    -0.60
     Sosten
    -0.60
    ']))
    
    -0.59
     Cassini
    -0.59
     }}}
    -0.58
     auctions
    -0.57
    POSITIVE LOGITS
    corer
    0.48
    #+#
    0.46
     Are
    0.45
    ourable
    0.43
     خارجية
    0.42
     very
    0.42
    SceneManagement
    0.42
    otides
    0.41
    Zdroj
    0.40
     consum
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.