© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76168
    Prev
    Next
    INDEX
    Explanations

    describing qualities/abilities

    np_max-act-logits · 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
    CloseOperation
    -0.69
     néz
    -0.68
    encodeWith
    -0.68
     quæ
    -0.64
     HomeComponent
    -0.63
     purity
    -0.60
    Personensuche
    -0.60
    Демографія
    -0.60
    ссора
    -0.60
     JAXBElement
    -0.59
    POSITIVE LOGITS
     ad
    0.54
     doInBackground
    0.48
     gifted
    0.47
     ddelweddau
    0.47
    TagMode
    0.47
    ad
    0.46
    了
    0.44
    tagHelper
    0.42
     fleet
    0.42
    able
    0.41
    Activations Density 0.001%

    No Known Activations