© 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. 91308
    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
    pas
    -0.53
     les
    -0.49
     and
    -0.49
     pas
    -0.47
    CrossRef
    -0.47
    kasten
    -0.47
     mol
    -0.45
    htë
    -0.45
    account
    -0.45
     geen
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    0.87
    
    0.69
     contextLoads
    0.69
     للمعارف
    0.68
    SharedDtor
    0.67
    PerformLayout
    0.66
    vician
    0.65
    featureID
    0.65
     AssemblyVersion
    0.64
    )++;
    0.61
    Activations Density 0.000%

    No Known Activations