© 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. 4-CLT-HP
    4. 2290
    Prev
    Next
    INDEX
    Explanations

    establishing something

    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
    locene
    -0.53
    bidities
    -0.52
     ujednoznacz
    -0.51
    tığı
    -0.51
    WriteBarrier
    -0.50
    phrine
    -0.49
     البعض
    -0.49
    racene
    -0.49
    CreateModel
    -0.49
    loroethane
    -0.49
    POSITIVE LOGITS
     any
    0.70
     of
    0.66
    ########.
    0.66
    IVEREF
    0.64
    Portail
    0.64
    出版年
    0.61
     незавершена
    0.56
     qualunque
    0.55
     apapun
    0.54
    any
    0.54
    Activations Density 0.005%

    No Known Activations