© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 94573
    Prev
    Next
    INDEX
    Explanations

    code/paths

    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
     ModelExpression
    -0.75
     AssemblyCulture
    -0.66
     وتسجيلات
    -0.62
     صوتيه
    -0.60
     chi̍t
    -0.56
     AssemblyProduct
    -0.56
     Paglinawan
    -0.55
     Fresh
    -0.53
     iſt
    -0.52
     Diſ
    -0.52
    POSITIVE LOGITS
     from
    0.72
     unto
    0.61
     as
    0.54
    from
    0.52
     round
    0.51
     on
    0.49
     Deum
    0.48
    putan
    0.48
     out
    0.47
     only
    0.47
    Activations Density 0.004%

    No Known Activations