© 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. 98129
    Prev
    Next
    INDEX
    Explanations

    pharmaceuticals

    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
     used
    -0.57
     of
    -0.55
     prescribed
    -0.54
    Used
    -0.53
    XmlAccessType
    -0.52
     Used
    -0.49
    Примечания
    -0.49
     Juifs
    -0.49
    发表于
    -0.49
    ScopeManager
    -0.49
    POSITIVE LOGITS
    ритори
    0.54
     Kuru
    0.52
    MemoryWarning
    0.51
    SerializedSize
    0.51
    ustimmung
    0.49
    aktur
    0.48
    ProgressHUD
    0.48
     Wachs
    0.47
    EDEFAULT
    0.47
    Untitled
    0.47
    Activations Density 0.001%

    No Known Activations