© 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. 38320
    Prev
    Next
    INDEX
    Explanations

    according

    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
    According
    -0.86
    according
    -0.76
     According
    -0.73
     according
    -0.70
     ACCORD
    -0.68
     acordo
    -0.68
    postolic
    -0.66
     menurut
    -0.64
     ifølge
    -0.62
    según
    -0.61
    POSITIVE LOGITS
     to
    1.71
    to
    0.69
    到
    0.59
     To
    0.58
     TO
    0.57
     thereto
    0.56
     toa
    0.54
     tot
    0.51
    tothe
    0.51
     к
    0.49
    Activations Density 0.022%

    No Known Activations