© 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. 38943
    Prev
    Next
    INDEX
    Explanations

    Scientific articles

    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
    urb
    -0.61
    Realistic
    -0.57
     RemoteException
    -0.56
     doInBackground
    -0.56
    ابل
    -0.54
    存于互联网档案馆
    -0.53
    AccessFile
    -0.51
    ровки
    -0.50
    SharedDtor
    -0.49
    так
    -0.49
    POSITIVE LOGITS
    forChild
    0.59
    żesz
    0.54
     chande
    0.54
     viewDidLoad
    0.51
    tvguidetime
    0.51
     تضيفلها
    0.50
     menudo
    0.49
    áč
    0.49
    cinia
    0.48
     correctes
    0.47
    Activations Density 1.566%

    No Known Activations