© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92115
    Prev
    Next
    INDEX
    Explanations

    ground

    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
     guidelines
    -0.63
     principles
    -0.55
    WindowConstants
    -0.52
    UnknownFields
    -0.52
     principle
    -0.49
     guideline
    -0.48
     priority
    -0.45
    RegistryLite
    -0.45
     reci
    -0.45
     nghề
    -0.45
    POSITIVE LOGITS
    WithIOException
    0.78
    ContentAsync
    0.76
     ujednoznacz
    0.73
     ostavi
    0.69
    GOTREF
    0.67
     AssemblyCompany
    0.66
     betweenstory
    0.64
     Infórmanos
    0.63
     consultato
    0.61
    yntaxException
    0.61
    Activations Density 0.005%

    No Known Activations