© 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. 0-CLT-HP
    7. 42914
    Prev
    Next
    INDEX
    Explanations

    cellular

    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
    DoubleQuotes
    -0.82
    MessageTagHelper
    -0.81
     متعلقه
    -0.77
     @"/
    -0.75
    ngdoc
    -0.75
     transférez
    -0.75
     gainera
    -0.71
    GraphicsUnit
    -0.71
     nahilalakip
    -0.71
     <>",
    -0.71
    POSITIVE LOGITS
     and
    0.46
     vaih
    0.42
    Arist
    0.38
    apropri
    0.36
    हि
    0.35
    X
    0.35
    A
    0.34
    וכ
    0.34
    N
    0.34
     pää
    0.34
    Activations Density 0.187%

    No Known Activations