© 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. 4384
    Prev
    Next
    INDEX
    Explanations

    cottage

    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
     précédents
    -0.60
     prêtres
    -0.55
    verwijspagina
    -0.55
     scolaires
    -0.55
    ahu
    -0.53
     siguran
    -0.53
    الحياه
    -0.52
    يكب
    -0.51
     Réponses
    -0.51
    BeginContext
    -0.50
    POSITIVE LOGITS
    core
    0.67
     industries
    0.64
     industry
    0.57
     Industries
    0.57
     core
    0.55
    y
    0.55
    grees
    0.53
    ware
    0.52
    wares
    0.52
     cheese
    0.51
    Activations Density 0.006%

    No Known Activations