© 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. 1380
    Prev
    Next
    INDEX
    Explanations

    sentences containing "has"

    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
     autorytatywna
    -0.89
     intptr
    -0.88
    #+#
    -0.85
    脚注の使い方
    -0.63
     ſeveral
    -0.63
    ourites
    -0.63
     الرخصة
    -0.63
    protoimpl
    -0.62
    posedge
    -0.62
    mobileqq
    -0.62
    POSITIVE LOGITS
    QueryParam
    0.45
     me
    0.44
     definitiv
    0.42
    힙
    0.42
     built
    0.42
    oar
    0.42
     relevance
    0.41
     definitely
    0.40
     saya
    0.40
     Fringe
    0.40
    Activations Density 0.003%

    No Known Activations