© 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. 43647
    Prev
    Next
    INDEX
    Explanations

    pylori

    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
     hug
    -0.86
     Hug
    -0.84
    脚注の使い方
    -0.81
     boomers
    -0.77
    Hug
    -0.72
     Wicidata
    -0.69
     doubtnut
    -0.67
    RTEE
    -0.67
    JpaRepository
    -0.65
    unknownFields
    -0.64
    POSITIVE LOGITS
     Meksiku
    0.54
    BeginContext
    0.53
    i
    0.52
    e
    0.48
    ellate
    0.46
    toHave
    0.43
     arşivlendi
    0.43
    SequentialGroup
    0.42
     transfieras
    0.42
     AB
    0.41
    Activations Density 1.038%

    No Known Activations