© 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. 4-CLT-HP
    7. 2810
    Prev
    Next
    INDEX
    Explanations

    Spanish expressions

    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
    таратура
    -0.65
    UserScript
    -0.61
     menj
    -0.60
     useRef
    -0.56
    ertos
    -0.54
     Catawiki
    -0.54
    Personensuche
    -0.52
     Kond
    -0.52
    MockBean
    -0.52
     ffilmiau
    -0.52
    POSITIVE LOGITS
    клопе
    0.63
     how
    0.54
     what
    0.50
     betreff
    0.50
     define
    0.50
    think
    0.50
    saying
    0.48
     redefine
    0.48
    ыре
    0.48
     replicate
    0.47
    Activations Density 0.014%

    No Known Activations