© 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. 91022
    Prev
    Next
    INDEX
    Explanations

    appellant

    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
     nôtre
    -0.98
     fumée
    -0.95
     armée
    -0.94
     autorité
    -0.93
     équilibre
    -0.89
     équipe
    -0.87
     mauva
    -0.87
     bonté
    -0.87
     poussière
    -0.86
     stessi
    -0.85
    POSITIVE LOGITS
     lot
    0.64
     known
    0.59
     for
    0.56
     of
    0.55
     has
    0.55
     more
    0.54
     similar
    0.54
     he
    0.53
    ,
    0.53
     rather
    0.52
    Activations Density 0.850%

    No Known Activations