© 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. 96093
    Prev
    Next
    INDEX
    Explanations

    the

    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
     isEqualToString
    -0.44
    openConnection
    -0.43
    ,:),
    -0.41
    nvarchar
    -0.41
     Cults
    -0.40
    ละเอียด
    -0.39
     ujednoznacz
    -0.39
    endphp
    -0.39
     подробно
    -0.38
     fallecimiento
    -0.38
    POSITIVE LOGITS
    AddTagHelper
    0.79
    原始内容存档于
    0.73
    WriteTagHelper
    0.70
     waiting
    0.62
     comfort
    0.60
    WebVitals
    0.59
    ComponentName
    0.59
     useAuth
    0.57
     Waiting
    0.56
     Safety
    0.55
    Activations Density 0.003%

    No Known Activations