© 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. 1404
    Prev
    Next
    INDEX
    Explanations

    limate

    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
     avoient
    -0.92
     étoient
    -0.92
     enfans
    -0.85
     feroit
    -0.84
     démocr
    -0.82
     auroit
    -0.81
     étoit
    -0.80
     quelcon
    -0.77
     normaux
    -0.75
     pitié
    -0.74
    POSITIVE LOGITS
    e
    1.11
    o
    0.99
    y
    0.87
    en
    0.84
    a
    0.83
    i
    0.82
    es
    0.65
    er
    0.65
    ه
    0.63
    t
    0.61
    Activations Density 0.130%

    No Known Activations