© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93277
    Prev
    Next
    INDEX
    Explanations

    verbs of action

    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
     Audiodateien
    -0.72
    kháu
    -0.67
    tonsoft
    -0.64
    Espèce
    -0.64
    MessageTagHelper
    -0.63
     يتيمه
    -0.61
     <>",
    -0.60
    webElementXpaths
    -0.60
     BorderSide
    -0.59
     GenerationType
    -0.59
    POSITIVE LOGITS
     us
    0.68
     нам
    0.54
     our
    0.49
     nations
    0.48
     new
    0.46
     ours
    0.46
     so
    0.45
     impossible
    0.44
     Nations
    0.43
     im
    0.43
    Activations Density 0.002%

    No Known Activations