© 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. 3296
    Prev
    Next
    INDEX
    Explanations

    wave

    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
     terület
    -0.49
     دیکھیے
    -0.46
    näm
    -0.43
     méri
    -0.42
    logy
    -0.42
     modalités
    -0.42
     épreuves
    -0.41
     fidèles
    -0.40
     uğ
    -0.39
     sedia
    -0.39
    POSITIVE LOGITS
     Мексичка
    0.91
     تضيفلها
    0.84
    HtmlAttribute
    0.77
    
    0.75
    Personensuche
    0.73
    SharedCtor
    0.73
    RetentionPolicy
    0.71
    UserScript
    0.71
    ^(@)
    0.71
    DockStyle
    0.70
    Activations Density 0.003%

    No Known Activations