© 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. 4934
    Prev
    Next
    INDEX
    Explanations

    numbers and articles

    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
    RectangleBorder
    -0.65
     getItemId
    -0.58
    orianCalendar
    -0.58
     للمعارف
    -0.57
    FormState
    -0.57
     surfers
    -0.55
     surf
    -0.54
     surfer
    -0.52
     متعلقه
    -0.52
     nonatomic
    -0.51
    POSITIVE LOGITS
    EndContext
    0.61
    TagHelper
    0.56
    öhnt
    0.49
    tagName
    0.49
    |+\
    0.47
     Administrativna
    0.47
     géné
    0.45
     herbe
    0.44
    θρω
    0.44
    ngel
    0.44
    Activations Density 0.001%

    No Known Activations