© 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. 4-CLT-HP
    7. 3355
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
    Extinguishing
    -0.69
     ویکی‌آمباردا
    -0.67
    FunctionFlags
    -0.67
     المعيارى
    -0.66
    <bos>
    -0.64
     ivelany
    -0.64
    minecraftforge
    -0.64
    нциклопе
    -0.61
    ьаж
    -0.60
     насељу
    -0.60
    POSITIVE LOGITS
     no
    0.70
     less
    0.52
     time
    0.50
     нет
    0.50
     none
    0.50
     keine
    0.49
     nobody
    0.48
     niente
    0.48
     kein
    0.47
    ]--;
    0.47
    Activations Density 0.004%

    No Known Activations