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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92203
    Prev
    Next
    INDEX
    Explanations

    never/once

    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
    running
    -0.64
     receiving
    -0.57
    Came
    -0.56
     came
    -0.56
    receiving
    -0.55
     CAME
    -0.55
     gaining
    -0.54
     running
    -0.52
    selling
    -0.52
     possessing
    -0.51
    POSITIVE LOGITS
    esgue
    0.72
    Filmografie
    0.69
    SharedDtor
    0.68
    RegistryLite
    0.64
    encodeWith
    0.63
    IsMutable
    0.63
    complexContent
    0.62
    ValueStyle
    0.62
     crdi
    0.61
     ?',
    0.61
    Activations Density 0.258%

    No Known Activations