© 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. 0-CLT-HP
    7. 40109
    Prev
    Next
    INDEX
    Explanations

    scientific text

    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
     protoimpl
    -0.86
    berdayakan
    -0.86
     beginnetje
    -0.86
    iffance
    -0.85
     Majefty
    -0.82
     bunting
    -0.82
    Còn
    -0.81
     Jefus
    -0.79
    haustible
    -0.79
     Monfieur
    -0.79
    POSITIVE LOGITS
    er
    0.94
    en
    0.90
    y
    0.88
    s
    0.84
    t
    0.73
    i
    0.68
    u
    0.66
    n
    0.66
    e
    0.63
    in
    0.62
    Activations Density 0.031%

    No Known Activations