© 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. 92283
    Prev
    Next
    INDEX
    Explanations

    accelerating

    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
    ware
    -0.69
     protecting
    -0.57
     guarding
    -0.57
     consuming
    -0.57
     accelerating
    -0.53
    case
    -0.46
    日閲覧
    -0.45
    ful
    -0.44
    ness
    -0.44
     hiér
    -0.44
    POSITIVE LOGITS
    oa̍t
    0.77
    Хьажоргаш
    0.68
    kloped
    0.67
    WebElementEntity
    0.63
    NameInMap
    0.60
    omiast
    0.60
    Autoritní
    0.60
     Italijanski
    0.60
    RegistryLite
    0.60
     TestBed
    0.59
    Activations Density 0.029%

    No Known Activations