© 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. 1182
    Prev
    Next
    INDEX
    Explanations

    names

    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
     grat
    -0.51
     QCD
    -0.48
     rumors
    -0.48
     chargers
    -0.48
     tang
    -0.48
     charging
    -0.48
     GAD
    -0.47
     implies
    -0.47
     parecia
    -0.47
     schreibt
    -0.47
    POSITIVE LOGITS
     WaitForSeconds
    0.50
     विश्वसनीयता
    0.50
    AxisAlignment
    0.50
    
    0.49
     AssemblyVersion
    0.47
     AssemblyTitle
    0.47
    
    0.47
    ۪
    0.45
    Legături
    0.44
     &___
    0.44
    Activations Density 0.025%

    No Known Activations