© 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. 1-CLT-HP
    7. 9471
    Prev
    Next
    INDEX
    Explanations

    biology and genetics

    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
     Wnt
    -0.99
    ItemBackground
    -0.84
     autorytatywna
    -0.80
    SharedCtor
    -0.78
     ddelweddau
    -0.75
    ArgsConstructor
    -0.75
    Personendaten
    -0.74
     שוליים
    -0.71
    parsedMessage
    -0.71
    SourceChecksum
    -0.71
    POSITIVE LOGITS
    /
    0.59
     amp
    0.54
     Amp
    0.52
    3
    0.52
     fim
    0.50
    Max
    0.49
    5
    0.49
    +
    0.49
    1
    0.49
    Amp
    0.48
    Activations Density 0.166%

    No Known Activations