© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97364
    Prev
    Next
    INDEX
    Explanations

    which

    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
     which
    -1.26
    which
    -1.05
     WHICH
    -0.97
     Which
    -0.95
    Which
    -0.92
     mely
    -0.70
    hich
    -0.68
    quelles
    -0.65
    ซึ่ง
    -0.62
     wich
    -0.60
    POSITIVE LOGITS
     have
    0.85
     are
    0.84
     has
    0.72
     were
    0.72
     Armenians
    0.66
     owes
    0.65
     Serbs
    0.65
     serves
    0.65
     had
    0.63
     gives
    0.63
    Activations Density 0.023%

    No Known Activations