© 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. 3350
    Prev
    Next
    INDEX
    Explanations

    code lists

    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
    protoimpl
    -0.68
    IonicModule
    -0.62
    jspx
    -0.58
    __":
    -0.58
     invokingState
    -0.58
    TagMode
    -0.57
     oprot
    -0.56
    CloseOperation
    -0.56
     resourceCulture
    -0.54
     onOptions
    -0.53
    POSITIVE LOGITS
    AnchorTagHelper
    0.50
    engkapi
    0.48
     esigenze
    0.48
     لينك
    0.47
    outWeight
    0.47
     voren
    0.47
     disant
    0.46
     atteinte
    0.46
     товар
    0.45
     and
    0.45
    Activations Density 0.002%

    No Known Activations