© 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. 97302
    Prev
    Next
    INDEX
    Explanations

    deuter

    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
    AndEndTag
    -0.70
     chré
    -0.67
     itſelf
    -0.66
     Cæsar
    -0.65
     leaſt
    -0.64
     cauſe
    -0.63
     Chriftian
    -0.63
     Reſ
    -0.63
     Theſe
    -0.63
     ſtre
    -0.61
    POSITIVE LOGITS
     Ne
    0.65
    mberto
    0.60
     Sta
    0.59
     MessageBoxIcon
    0.56
     Pe
    0.56
     De
    0.54
    copes
    0.54
    rachtet
    0.53
    tificates
    0.53
     ProtoMessage
    0.52
    Activations Density 0.155%

    No Known Activations