© 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. 1996
    Prev
    Next
    INDEX
    Explanations

    than

    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
     than
    -1.59
    than
    -1.07
     niż
    -1.00
     THAN
    -1.00
     kuin
    -0.98
    Than
    -0.96
     än
    -0.93
     než
    -0.88
    жели
    -0.85
     decât
    -0.84
    POSITIVE LOGITS
     the
    1.23
     those
    0.97
     one
    0.92
     
    0.89
     a
    0.81
     its
    0.79
     this
    0.77
     their
    0.77
     any
    0.77
     original
    0.75
    Activations Density 0.047%

    No Known Activations