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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12548
    Prev
    Next
    INDEX
    Explanations

    Eating/taking in

    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
     Schub
    -0.62
    WaitGroup
    -0.59
     iſt
    -0.59
    θεια
    -0.59
     Jefus
    -0.59
    asyarakat
    -0.55
     pleaſure
    -0.55
    spesies
    -0.54
     betweenstory
    -0.53
     muſt
    -0.52
    POSITIVE LOGITS
     وتسجيلات
    0.60
    Portail
    0.56
     injury
    0.53
     JAXBElement
    0.52
    kloped
    0.52
     אביב
    0.51
     Injury
    0.51
    CodedInputStream
    0.51
    cito
    0.49
     Injuries
    0.49
    Activations Density 0.023%

    No Known Activations