© 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. 97748
    Prev
    Next
    INDEX
    Explanations

    aromatic

    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
     feroit
    -1.10
     auroit
    -1.09
    endphp
    -1.08
     avoient
    -1.05
     chré
    -1.02
     pouvoit
    -1.00
     fédé
    -0.98
    Personendaten
    -0.97
     étoient
    -0.96
     fumée
    -0.96
    POSITIVE LOGITS
     material
    0.62
     che
    0.50
     new
    0.48
     double
    0.47
     but
    0.47
     and
    0.47
     p
    0.46
     ri
    0.46
     il
    0.46
     load
    0.46
    Activations Density 0.096%

    No Known Activations