© 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. 0-CLT-HP
    7. 45317
    Prev
    Next
    INDEX
    Explanations

    zing

    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
    zing
    -1.60
     Quarter
    -1.14
     Executive
    -1.06
     executive
    -1.02
    Quarter
    -1.00
     quarter
    -0.94
    Executive
    -0.92
     Quarters
    -0.91
    ZING
    -0.90
     quarters
    -0.88
    POSITIVE LOGITS
    enderror
    0.65
    Autoritní
    0.62
     chi̍t
    0.57
    rencies
    0.56
    Спасылкі
    0.56
    
    0.53
     CLR
    0.52
    +#+#
    0.52
    ities
    0.50
    middels
    0.50
    Activations Density 0.694%

    No Known Activations