© 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. 5782
    Prev
    Next
    INDEX
    Explanations

    Code/license related texts

    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
     تضيفلها
    -0.79
     wireType
    -0.71
     resourceCulture
    -0.71
     виправивши
    -0.69
     transférez
    -0.68
    ">//
    -0.61
    +#+#
    -0.59
    WebServlet
    -0.59
    Then
    -0.58
     was
    -0.58
    POSITIVE LOGITS
    <bos>
    0.65
     entrepreneurs
    0.60
     in
    0.60
     agriculture
    0.53
    Filmografie
    0.52
     Christianity
    0.52
     Stefani
    0.52
     businesses
    0.52
     Antioch
    0.52
     dago
    0.52
    Activations Density 0.001%

    No Known Activations