© 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. 1-CLT-HP
    7. 496
    Prev
    Next
    INDEX
    Explanations

    Scientific/chemical terms

    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
    .*")]
    -0.83
     ProtoMessage
    -0.76
     betweenstory
    -0.72
    webElementXpaths
    -0.72
     فريبيس
    -0.68
    ConstraintMaker
    -0.68
    protoimpl
    -0.67
    AnchorStyles
    -0.66
    InvalidProtocol
    -0.66
    DockStyle
    -0.64
    POSITIVE LOGITS
    ed
    0.52
    eo
    0.49
    eur
    0.47
    wo
    0.47
    ide
    0.45
     mix
    0.44
     diagrama
    0.44
    pura
    0.44
    urilor
    0.44
    ides
    0.43
    Activations Density 0.029%

    No Known Activations