© 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. 42038
    Prev
    Next
    INDEX
    Explanations

    smell

    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
     smell
    -2.03
    smell
    -1.73
     smells
    -1.66
     Smell
    -1.60
     severity
    -1.55
     ſever
    -1.52
     smelled
    -1.45
     Monfieur
    -1.45
     fevere
    -1.40
     odour
    -1.40
    POSITIVE LOGITS
    ,
    0.84
     (
    0.81
     and
    0.75
     under
    0.68
     
    0.65
    .
    0.63
    s
    0.62
    den
    0.59
     in
    0.58
     +
    0.58
    Activations Density 0.323%

    No Known Activations