© 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. 20-CLT-HP
    7. 77887
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · 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
    openSession
    -0.56
    rimo
    -0.53
     brach
    -0.51
    breakable
    -0.50
    bunda
    -0.49
     libri
    -0.49
    rima
    -0.48
     ouvertes
    -0.47
     escritura
    -0.47
    oose
    -0.47
    POSITIVE LOGITS
     >=",
    0.73
    MENAFN
    0.72
     OFDb
    0.63
    EDEFAULT
    0.63
    setVerticalGroup
    0.62
    WindowConstants
    0.59
    InSection
    0.56
    ClientSize
    0.56
     Ganz
    0.54
     ModelExpression
    0.53
    Activations Density 0.000%

    No Known Activations