© 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. 93978
    Prev
    Next
    INDEX
    Explanations

    scientific experiments

    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
     TestBed
    -0.91
    expandindo
    -0.90
    InitVars
    -0.84
     intptr
    -0.82
     lenker
    -0.82
    queryInterface
    -0.82
    出版年
    -0.79
    setVerticalGroup
    -0.79
     StatelessWidget
    -0.79
    SourceChecksum
    -0.77
    POSITIVE LOGITS
     you
    0.75
     the
    0.72
    <bos>
    0.71
     this
    0.63
     your
    0.63
    this
    0.63
    you
    0.59
    the
    0.59
     I
    0.58
     there
    0.58
    Activations Density 0.021%

    No Known Activations