© 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. 5-CLT-HP
    7. 2114
    Prev
    Next
    INDEX
    Explanations

    hearing and communication

    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
     hears
    -0.77
    AddTagHelper
    -0.70
    👂
    -0.63
     AudioClip
    -0.62
     Hearing
    -0.58
     hear
    -0.58
    AndEndTag
    -0.57
     listens
    -0.56
     mendengar
    -0.56
     hearing
    -0.55
    POSITIVE LOGITS
    ("&
    0.54
    看來
    0.53
    Personensuche
    0.53
    IUrlHelper
    0.50
     visibility
    0.50
    互
    0.49
     Dude
    0.48
     Yel
    0.48
    üyada
    0.47
    chartInstance
    0.47
    Activations Density 0.008%

    No Known Activations