© 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. 77084
    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
     onCancelled
    -0.72
     chi̍t
    -0.71
     typelib
    -0.71
    erializer
    -0.68
     PyLong
    -0.67
    Jereo
    -0.67
     насељу
    -0.66
    iastes
    -0.65
    ęku
    -0.65
    achusetts
    -0.64
    POSITIVE LOGITS
     working
    0.63
     left
    0.62
    working
    0.51
     Working
    0.50
     Left
    0.47
    Working
    0.46
     trades
    0.45
     T
    0.45
     Leave
    0.43
    KURZBESCHREIBUNG
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.