© 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. 14342
    Prev
    Next
    INDEX
    Explanations

    health

    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
    ніципа
    -0.62
     scin
    -0.61
    
    -0.55
     utafitiHapana
    -0.52
    AndEndTag
    -0.52
    webElementGuid
    -0.51
    ră
    -0.51
     propOrder
    -0.50
    ($_
    -0.48
     such
    -0.47
    POSITIVE LOGITS
    tillation
    0.61
     helst
    0.57
     يتيمه
    0.56
    reszcie
    0.55
     vectoriales
    0.54
     domésticos
    0.53
    zeitige
    0.53
    égration
    0.50
    moiselle
    0.50
    ORIAL
    0.50
    Activations Density 0.142%

    No Known Activations