© 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. 5-CLT-HP
    7. 94945
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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
     متعلقه
    -0.75
    
    -0.71
     فريبيس
    -0.69
    __":
    -0.66
     AssemblyTitle
    -0.65
    ContentAsync
    -0.61
    __':
    -0.60
     tartalomajánló
    -0.59
     chi̍t
    -0.57
    __":
    -0.54
    POSITIVE LOGITS
     crushed
    0.54
     ground
    0.54
     natural
    0.52
     lenker
    0.51
    Inflater
    0.49
     dehydrated
    0.49
     dried
    0.49
     fermented
    0.49
     concentrated
    0.49
     real
    0.49
    Activations Density 0.001%

    No Known Activations