Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44317
    Prev
    Next
    INDEX
    Explanations

    capacity and self

    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
     self
    -0.53
    self
    -0.52
    bids
    -0.50
    ModelAdmin
    -0.50
    ModelSerializer
    -0.49
    FieldDescriptor
    -0.46
     назначения
    -0.45
    errHandler
    -0.45
    пусти
    -0.45
     Capacity
    -0.44
    POSITIVE LOGITS
     informée
    0.61
    IsContent
    0.60
     sucrose
    0.59
     sphinct
    0.59
     estekak
    0.58
    /*
    0.57
     measles
    0.57
     chert
    0.57
     ویکی‌پدیا
    0.57
     برانيه
    0.57
    Activations Density 0.066%

    No Known Activations