© 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. 38619
    Prev
    Next
    INDEX
    Explanations

    Portrait

    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
    s
    -0.65
     James
    -0.50
    a
    -0.45
    ing
    -0.44
    abit
    -0.43
    ی
    -0.43
    ,
    -0.43
     plus
    -0.40
    ait
    -0.40
    sus
    -0.40
    POSITIVE LOGITS
     Monfieur
    1.02
    Zeneca
    0.94
    ^(@)
    0.91
     Shakspeare
    0.90
    RTLD
    0.89
     myſelf
    0.84
    IsContent
    0.83
     насељу
    0.83
    日閲覧
    0.82
    Datuak
    0.82
    Activations Density 0.320%

    No Known Activations