© 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. 4-CLT-HP
    7. 1107
    Prev
    Next
    INDEX
    Explanations

    Japanese

    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
     mukana
    -0.53
     District
    -0.52
     newBuilder
    -0.47
     Pfar
    -0.47
     Polsek
    -0.46
     szob
    -0.45
    tagHelperRunner
    -0.45
     izvē
    -0.44
     الرياضيه
    -0.44
     Transfermarkt
    -0.44
    POSITIVE LOGITS
    出版年
    0.66
    ActionCreators
    0.63
     things
    0.60
     THINGS
    0.58
     thing
    0.58
    styleable
    0.56
    MessageTagHelper
    0.56
    事
    0.53
     Things
    0.53
    things
    0.52
    Activations Density 0.002%

    No Known Activations