© 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. 39920
    Prev
    Next
    INDEX
    Explanations

    sustainable

    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
    Sustainable
    -1.09
     sustainable
    -1.06
    sustainable
    -1.05
     sustainably
    -1.03
     للمعارف
    -0.98
     sostenible
    -0.96
     étoit
    -0.95
     Sustainable
    -0.94
     Alternative
    -0.93
     auroit
    -0.92
    POSITIVE LOGITS
     background
    0.48
     rest
    0.47
     leth
    0.47
     embar
    0.46
    InstanceState
    0.46
     newInstance
    0.45
     situation
    0.44
     progress
    0.44
     reason
    0.43
     Sul
    0.43
    Activations Density 0.371%

    No Known Activations