© 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. 14538
    Prev
    Next
    INDEX
    Explanations

    Scientific/Medical 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
     BorderRadius
    -0.58
    lgari
    -0.52
    enumi
    -0.49
    LookAndFeel
    -0.47
     MonoBehaviour
    -0.47
    ThroughAttribute
    -0.45
    lapsingToolbar
    -0.45
    nå
    -0.44
     onCreateView
    -0.42
    APORE
    -0.42
    POSITIVE LOGITS
    parsedMessage
    0.73
     Cuth
    0.63
    Демографія
    0.63
    όρ
    0.63
    =$?
    0.61
     suaminya
    0.61
     Autorizaciones
    0.60
     referenties
    0.60
    ViewChild
    0.57
    Искәрмәләр
    0.57
    Activations Density 0.145%

    No Known Activations