© 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. 39939
    Prev
    Next
    INDEX
    Explanations

    possessed

    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
     démocr
    -1.12
     precisione
    -1.09
     morire
    -1.08
     تانيه
    -1.04
     étoient
    -1.03
     Juifs
    -1.02
     automatiques
    -1.02
     chré
    -1.02
    included
    -1.02
     varandra
    -1.00
    POSITIVE LOGITS
     by
    0.61
    ness
    0.60
     bu
    0.58
     me
    0.57
     cha
    0.57
    ité
    0.57
     th
    0.55
     fu
    0.55
     o
    0.54
     us
    0.54
    Activations Density 0.038%

    No Known Activations