© 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. 981
    Prev
    Next
    INDEX
    Explanations

    time, dates, events

    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
    Datuak
    -0.55
    WebVitals
    -0.52
     strerror
    -0.46
     PLUS
    -0.45
    MLLoader
    -0.44
     QtCore
    -0.44
     للمعارف
    -0.44
    WaitGroup
    -0.44
     doInBackground
    -0.43
    IntoConstraints
    -0.43
    POSITIVE LOGITS
    Rüyada
    0.71
     mauvaises
    0.63
     propOrder
    0.62
     élevées
    0.60
     CWE
    0.58
    gesteld
    0.57
     bakgrund
    0.57
    $_['
    0.57
     "..\..\
    0.56
    .'.
    0.56
    Activations Density 0.002%

    No Known Activations