© 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. 5262
    Prev
    Next
    INDEX
    Explanations

    to and with

    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
     do
    -0.86
     are
    -0.71
     come
    -0.68
     be
    -0.63
     have
    -0.62
     will
    -0.58
     find
    -0.56
     can
    -0.54
     is
    -0.53
     share
    -0.51
    POSITIVE LOGITS
    OGND
    1.04
    BeginContext
    1.02
     Efq
    0.98
     fubject
    0.98
     perfons
    0.95
    EDEFAULT
    0.94
    fjspx
    0.92
     pleaſure
    0.90
    writeField
    0.89
    DoubleQuotes
    0.88
    Activations Density 0.003%

    No Known Activations