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. 0-CLT-HP
    4. 44381
    Prev
    Next
    INDEX
    Explanations

    science and technology

    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
     Garfield
    -1.19
     Optic
    -1.05
     AssemblyTitle
    -0.99
     optic
    -0.95
    SharedDtor
    -0.83
    XmlAccessorType
    -0.74
    fjspx
    -0.71
    LayoutManager
    -0.70
    nościo
    -0.70
    PerformLayout
    -0.68
    POSITIVE LOGITS
     kool
    0.48
     Beb
    0.46
     CART
    0.41
    aData
    0.41
    Parent
    0.40
    IContainer
    0.39
     parental
    0.39
     nought
    0.38
    nya
    0.38
     unaff
    0.38
    Activations Density 0.287%

    No Known Activations