© 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. 644
    Prev
    Next
    INDEX
    Explanations

    did

    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
    ConstraintMaker
    -1.10
    SequentialGroup
    -0.95
    ScopeManager
    -0.94
     GenerationType
    -0.94
     المعيارى
    -0.93
    AddTagHelper
    -0.91
     الرياضيه
    -0.87
    новниш
    -0.85
    setopt
    -0.85
     فريبيس
    -0.84
    POSITIVE LOGITS
     mun
    0.36
    arned
    0.36
     mal
    0.33
     nons
    0.33
     en
    0.32
     only
    0.31
    chi
    0.31
    kü
    0.31
     n
    0.30
     bila
    0.30
    Activations Density 0.012%

    No Known Activations