© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10006
    Prev
    Next
    INDEX
    Explanations

    Vars

    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
     Paglinawan
    -0.71
     виправивши
    -0.65
    protoc
    -0.63
    OfWork
    -0.63
    مصادر
    -0.62
    shund
    -0.61
    İstinadlar
    -0.61
     joaat
    -0.60
    izarse
    -0.59
    XmlAccessType
    -0.58
    POSITIVE LOGITS
     wet
    0.44
    MLLoader
    0.42
     position
    0.42
    enzie
    0.41
     triad
    0.40
     Palatine
    0.40
     epis
    0.40
     sweat
    0.39
    epis
    0.39
     lī
    0.38
    Activations Density 0.121%

    No Known Activations