© 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. 92425
    Prev
    Next
    INDEX
    Explanations

    part

    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
    RenderAtEndOf
    -0.59
     betweenstory
    -0.59
    مصادر
    -0.50
     okuyayım
    -0.49
     skolen
    -0.47
    original
    -0.47
     facilmente
    -0.46
     hindurch
    -0.46
     snabbt
    -0.45
     tæn
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.56
     AssemblyVersion
    0.54
    ValueGeneration
    0.53
    withstanding
    0.53
    utentic
    0.51
    bnf
    0.51
    UniformLocation
    0.51
    WindowListener
    0.50
     وصلة
    0.50
    ContentAlignment
    0.49
    Activations Density 0.006%

    No Known Activations