© 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. 92509
    Prev
    Next
    INDEX
    Explanations

    possibilities and differences

    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
    <bos>
    -0.59
     options
    -0.53
     features
    -0.51
     dependencies
    -0.51
     loopholes
    -0.51
     parameters
    -0.51
     excuses
    -0.50
     issues
    -0.50
     deficiencies
    -0.49
     abilities
    -0.49
    POSITIVE LOGITS
    исленность
    0.75
     ujednoznacz
    0.74
     set
    0.61
    RenderAtEndOf
    0.60
    Portail
    0.59
     albeit
    0.59
    ptonshire
    0.59
    ardom
    0.58
    ViewSet
    0.57
    albeit
    0.57
    Activations Density 0.109%

    No Known Activations