© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1396
    Prev
    Next
    INDEX
    Explanations

    having

    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
    having
    -1.62
     Having
    -1.59
     having
    -1.56
    Having
    -1.50
     HAVING
    -1.25
     ayant
    -1.06
     avendo
    -0.96
     teniendo
    -0.91
     tendo
    -0.88
     habiendo
    -0.84
    POSITIVE LOGITS
     been
    0.80
     got
    0.63
     reached
    0.62
     to
    0.60
     occurred
    0.58
     gotten
    0.57
     remained
    0.55
     stayed
    0.52
     went
    0.49
     responded
    0.49
    Activations Density 0.496%

    No Known Activations