© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92829
    Prev
    Next
    INDEX
    Explanations

    of

    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
     الحره
    -1.06
     AssemblyTitle
    -0.79
    ,:);
    -0.69
     Wiktionnaire
    -0.69
    WriteTagHelper
    -0.69
    TagHelper
    -0.67
    InjectAttribute
    -0.65
    TableBody
    -0.64
    Гц
    -0.64
     the
    -0.63
    POSITIVE LOGITS
     élas
    0.47
    väg
    0.47
     épais
    0.47
     appena
    0.46
     more
    0.46
     lebih
    0.46
     μό
    0.45
     close
    0.44
     více
    0.44
     over
    0.42
    Activations Density 0.004%

    No Known Activations