© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 67
    Prev
    Next
    INDEX
    Explanations

    General text/statements

    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
    BeginContext
    -1.00
    SourceChecksum
    -0.83
    tagHelperRunner
    -0.77
     Roskov
    -0.73
     AssemblyVersion
    -0.72
     Normdatei
    -0.72
     angekommen
    -0.69
     Bourgoin
    -0.68
     MenuView
    -0.67
    ChildScrollView
    -0.66
    POSITIVE LOGITS
    Tied
    0.44
     similar
    0.43
    ounced
    0.42
     תא
    0.41
     če
    0.41
     Clarence
    0.39
     coin
    0.39
     fluor
    0.39
     şu
    0.38
    รง
    0.37
    Activations Density 0.019%

    No Known Activations