© 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. 5-CLT-HP
    7. 5888
    Prev
    Next
    INDEX
    Explanations

    image placement

    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
     these
    -0.43
     Wheatley
    -0.41
     the
    -0.41
     this
    -0.40
     gasoline
    -0.40
    грева
    -0.40
    readed
    -0.39
    นี้
    -0.39
    a
    -0.38
     Gorman
    -0.36
    POSITIVE LOGITS
     autorytatywna
    1.09
    Autoritní
    0.96
     ModelExpression
    0.88
     Мексичка
    0.86
    CppMethod
    0.82
     AssemblyCulture
    0.82
     HasFactory
    0.81
     otomatig
    0.81
    enumii
    0.81
     Biôgrafia
    0.78
    Activations Density 0.002%

    No Known Activations