© 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. 1-CLT-HP
    7. 13515
    Prev
    Next
    INDEX
    Explanations

    is

    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
     Knudsen
    -0.46
    Ssl
    -0.43
     pro
    -0.42
    بسم
    -0.42
    __':
    -0.41
     schi
    -0.41
    PSL
    -0.41
    prepareStatement
    -0.41
    μως
    -0.41
    kosi
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.72
    protoimpl
    0.68
    SerializedSize
    0.67
    kloped
    0.64
     незавершена
    0.64
    Personensuche
    0.63
    Tembelea
    0.61
    windowFixed
    0.60
     defaultstate
    0.60
    Viitteet
    0.60
    Activations Density 0.247%

    No Known Activations