© 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. 20-CLT-HP
    7. 74733
    Prev
    Next
    INDEX
    Explanations

    Awards

    np_max-act-logits · 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
     prizes
    -1.29
     prize
    -1.19
     winners
    -1.09
     Prizes
    -1.07
     winning
    -1.05
     Prize
    -1.05
     awards
    -1.04
     premios
    -1.03
     winner
    -1.02
     premio
    -1.00
    POSITIVE LOGITS
     déf
    0.40
     sàng
    0.39
    estination
    0.39
     sû
    0.39
     phthal
    0.39
     defaultstate
    0.38
     aéri
    0.37
    FL
    0.36
    denn
    0.36
    ziej
    0.35
    Activations Density 0.002%

    No Known Activations