© 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. 0-CLT-HP
    7. 93315
    Prev
    Next
    INDEX
    Explanations

    Contractions ending in "nt"

    np_max-act · gemini-2.0-flash
    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
     doesnt
    -1.63
    Dont
    -1.58
     couldnt
    -1.57
     youll
    -1.55
     Thats
    -1.55
     didnt
    -1.54
     isnt
    -1.54
     Dont
    -1.54
     wasnt
    -1.51
     dont
    -1.50
    POSITIVE LOGITS
    ly
    0.60
    se
    0.55
     a
    0.51
    zeits
    0.50
      
    0.50
     
    0.49
     the
    0.47
     con
    0.46
    ance
    0.46
     e
    0.45
    Activations Density 0.175%

    No Known Activations