© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97562
    Prev
    Next
    INDEX
    Explanations

    academic topics

    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
     myſelf
    -1.28
     Monfieur
    -1.16
     purpoſe
    -1.13
     themſelves
    -1.13
     himſelf
    -1.12
     itſelf
    -1.12
     Majefty
    -1.10
     Jefus
    -1.09
     ſtate
    -1.09
     pleaſure
    -1.09
    POSITIVE LOGITS
     la
    0.69
     def
    0.64
     Land
    0.61
     l
    0.60
     Des
    0.60
     
    0.57
     La
    0.56
     den
    0.56
     el
    0.55
     [
    0.54
    Activations Density 0.080%

    No Known Activations