© 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. 97490
    Prev
    Next
    INDEX
    Explanations

    Seats and backward direction

    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
     seat
    -0.79
     friend
    -0.73
     backwards
    -0.56
     friendship
    -0.51
     Friendship
    -0.51
    friendship
    -0.48
    Geografie
    -0.47
     foe
    -0.47
     civile
    -0.47
     FRIEND
    -0.46
    POSITIVE LOGITS
     GenerationType
    0.85
    ⓧ
    0.78
    ArgsConstructor
    0.78
     تانيه
    0.75
     odkazy
    0.74
    клопе
    0.68
     חיצוניים
    0.68
     للمعارف
    0.67
     चीज़ों
    0.67
    KommentareTeilen
    0.66
    Activations Density 0.138%

    No Known Activations