© 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. 4-CLT-HP
    7. 662
    Prev
    Next
    INDEX
    Explanations

    about

    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
     Roskov
    -0.77
    ^(@)
    -0.76
    CloseOperation
    -0.72
     tartalomajánló
    -0.70
    abestanden
    -0.69
    MemoryWarning
    -0.69
    NamedQueries
    -0.69
    новништво
    -0.69
     EconPapers
    -0.68
     AssemblyVersion
    -0.67
    POSITIVE LOGITS
     as
    0.76
     eight
    0.57
     eleven
    0.56
     seven
    0.55
     half
    0.54
     now
    0.53
     six
    0.52
     eighty
    0.52
     nine
    0.52
     once
    0.52
    Activations Density 0.002%

    No Known Activations