© 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. 90932
    Prev
    Next
    INDEX
    Explanations

    events and organizations

    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
     Jérusalem
    -0.64
    UAGE
    -0.59
    říklad
    -0.57
    SharedCtor
    -0.54
     rodríguez
    -0.54
     bunk
    -0.54
    hoid
    -0.54
     Monfieur
    -0.54
     ſind
    -0.52
     psychos
    -0.52
    POSITIVE LOGITS
    AnchorStyles
    0.58
    tvguidetime
    0.56
    SerializedSize
    0.49
    AddTagHelper
    0.48
     Affairs
    0.45
    ContentAsync
    0.45
     Program
    0.45
     EventHandler
    0.44
     protoimpl
    0.43
    ंदीखरीदारी
    0.43
    Activations Density 0.088%

    No Known Activations