© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43721
    Prev
    Next
    INDEX
    Explanations

    Permission or communication

    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
     approaches
    -0.78
     talks
    -0.71
     displays
    -0.69
     passes
    -0.61
     supplies
    -0.59
     exhibits
    -0.59
     exposes
    -0.58
     shows
    -0.58
     Approaches
    -0.57
     reveals
    -0.57
    POSITIVE LOGITS
    Notae
    0.84
     utafitiHapana
    0.76
     متعلقه
    0.71
    rungsseite
    0.68
    hirts
    0.68
    capes
    0.65
    cales
    0.63
    continence
    0.63
    Filmografie
    0.63
    seamnă
    0.62
    Activations Density 1.820%

    No Known Activations