© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75846
    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
     
    -0.69
    <bos>
    -0.63
    -
    -0.62
     “
    -0.58
     f
    -0.57
    </b>
    -0.56
     "
    -0.55
     In
    -0.53
     $
    -0.51
     p
    -0.51
    POSITIVE LOGITS
     myſelf
    1.55
     Efq
    1.55
     itſelf
    1.44
     themſelves
    1.43
     himſelf
    1.43
     becauſe
    1.41
     Monfieur
    1.41
     Jefus
    1.39
     whoſe
    1.36
     Majefty
    1.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.