© 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. 10231
    Prev
    Next
    INDEX
    Explanations

    code or technical descriptions

    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
     iStock
    -0.77
     persevere
    -0.53
    contentLoaded
    -0.47
    IRQn
    -0.44
     objectForKey
    -0.44
     ComVisible
    -0.43
    PMailer
    -0.43
    ustain
    -0.43
    invokeLater
    -0.42
    <%=
    -0.42
    POSITIVE LOGITS
     tartalomajánló
    0.91
    saraba
    0.69
     vectorielles
    0.69
    findpost
    0.68
     wikipagina
    0.65
    Przypisy
    0.63
     estekak
    0.61
    Einzelnachweise
    0.61
     препратки
    0.59
     وتسجيلات
    0.58
    Activations Density 0.416%

    No Known Activations