© 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. 5-CLT-HP
    7. 91597
    Prev
    Next
    INDEX
    Explanations

    medical or academic 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
    HasForeignKey
    -0.53
     Nich
    -0.50
    Initializable
    -0.47
    googleapis
    -0.44
    يميديا
    -0.43
     الميل
    -0.42
     familiarity
    -0.41
    displayquote
    -0.40
    contentInset
    -0.40
     Inspired
    -0.40
    POSITIVE LOGITS
     MainAxisSize
    0.71
     Picchu
    0.68
     InputDecoration
    0.68
     <<<<<<<<<<<<<<
    0.63
    ieteur
    0.62
    IVEREF
    0.61
    PyExc
    0.60
    kháu
    0.60
    rungsseite
    0.60
    contentLoaded
    0.59
    Activations Density 0.001%

    No Known Activations