© 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. 0-CLT-HP
    7. 95011
    Prev
    Next
    INDEX
    Explanations

    interact

    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
     interaction
    -2.25
    interaction
    -2.09
     interact
    -2.08
     interacted
    -2.08
     interacting
    -2.05
     interactions
    -1.95
     Interaction
    -1.94
     interacts
    -1.91
    Interaction
    -1.83
     Interactions
    -1.78
    POSITIVE LOGITS
     with
    0.92
     between
    0.69
     bet
    0.55
    ist
    0.52
    cault
    0.48
    igay
    0.47
     w
    0.47
     متعلقه
    0.47
    toggler
    0.45
     can
    0.43
    Activations Density 0.353%

    No Known Activations