© 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. 4088
    Prev
    Next
    INDEX
    Explanations

    technical/patent documents

    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
     tué
    -0.72
    @[+][
    -0.70
    OGND
    -0.68
     الرياضيه
    -0.65
    RetentionPolicy
    -0.62
     Roswell
    -0.58
     getItemId
    -0.57
     precisione
    -0.57
     funcionales
    -0.57
    glise
    -0.57
    POSITIVE LOGITS
    '
    0.56
     being
    0.52
     s
    0.52
     engaged
    0.51
     like
    0.50
    вЂ
    0.50
     scenario
    0.49
    ¿
    0.49
    `
    0.48
    ‟
    0.47
    Activations Density 0.002%

    No Known Activations