© 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. 15145
    Prev
    Next
    INDEX
    Explanations

    scientific/technical texts

    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
    queryInterface
    -0.79
     ―――――
    -0.71
     NavController
    -0.64
     IEEE
    -0.64
     ModelExpression
    -0.61
     necessaria
    -0.59
     Apothe
    -0.59
     Lame
    -0.59
     réglable
    -0.59
     RequestMethod
    -0.58
    POSITIVE LOGITS
     the
    0.48
     disk
    0.43
     more
    0.42
    disk
    0.41
     some
    0.41
     a
    0.40
     gar
    0.40
     his
    0.39
     this
    0.39
     their
    0.39
    Activations Density 0.019%

    No Known Activations