© 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. 5-CLT-HP
    7. 3968
    Prev
    Next
    INDEX
    Explanations

    habitat

    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
    WebServlet
    -0.57
    dafx
    -0.56
    __":
    -0.55
    teurs
    -0.54
    ciato
    -0.54
    τουργ
    -0.54
    cillor
    -0.52
    luor
    -0.50
    quine
    -0.49
    galo
    -0.49
    POSITIVE LOGITS
     territory
    0.60
     متعلقه
    0.53
    :✨
    0.52
     Importance
    0.51
     preference
    0.51
     grounds
    0.50
     surroundings
    0.50
    Географи
    0.50
     destruction
    0.50
     houſe
    0.50
    Activations Density 0.001%

    No Known Activations