© 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. 92031
    Prev
    Next
    INDEX
    Explanations

    shown

    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
     shown
    -2.42
    shown
    -2.06
     Shown
    -1.96
     depicted
    -1.88
     pictured
    -1.65
    Shown
    -1.52
     displayed
    -1.52
     portrayed
    -1.52
     shewn
    -1.52
     mostrado
    -1.45
    POSITIVE LOGITS
     by
    0.90
     to
    0.84
     the
    0.76
     
    0.75
     post
    0.73
     for
    0.70
     on
    0.68
     up
    0.67
     us
    0.66
     them
    0.65
    Activations Density 0.068%

    No Known Activations