© 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. 5-CLT-HP
    7. 2728
    Prev
    Next
    INDEX
    Explanations

    technology and research

    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
     cling
    -0.46
    NamedQueries
    -0.43
    Unmanaged
    -0.42
    éma
    -0.42
    PageModule
    -0.41
    onAttach
    -0.41
     soát
    -0.40
    ็จ
    -0.40
    copg
    -0.40
    hams
    -0.40
    POSITIVE LOGITS
    WriteBarrier
    0.78
     autorytatywna
    0.73
     Roskov
    0.71
     հղումներ
    0.66
    adget
    0.65
     Computers
    0.65
    पया
    0.62
    Ծանոթ
    0.62
     Robotics
    0.61
    verwijspagina
    0.60
    Activations Density 0.014%

    No Known Activations