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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2165
    Prev
    Next
    INDEX
    Explanations

    traditional/conventional

    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
    Traditional
    -0.90
    traditional
    -0.80
     Traditional
    -0.79
     traditional
    -0.75
     tradi
    -0.69
     TRAD
    -0.67
    tradition
    -0.66
     smtplib
    -0.65
    Conventional
    -0.65
     Traditionally
    -0.64
    POSITIVE LOGITS
     quæ
    0.68
    bigliamento
    0.60
    utebol
    0.59
     myſelf
    0.58
     againſt
    0.58
    letus
    0.57
     colorés
    0.57
     purpoſe
    0.54
     ſtate
    0.53
    Rohy
    0.53
    Activations Density 0.002%

    No Known Activations