© 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. 1287
    Prev
    Next
    INDEX
    Explanations

    Currency, Directions

    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
     west
    -0.75
    Arctic
    -0.59
    jooq
    -0.59
    ագրություններ
    -0.58
     typelib
    -0.58
     Arctic
    -0.55
     arctic
    -0.54
    west
    -0.52
    idosis
    -0.50
    /**
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.69
    mphony
    0.68
    SharedCtor
    0.65
    󠁴
    0.63
    Datuak
    0.56
    uxxxx
    0.54
    pleaños
    0.52
    XmlEnum
    0.52
    ficit
    0.51
    MLLoader
    0.50
    Activations Density 0.194%

    No Known Activations