© 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. 93979
    Prev
    Next
    INDEX
    Explanations

    Interact/Encounter

    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
    -1.85
    interaction
    -1.58
     Interaction
    -1.53
     interactions
    -1.52
     interact
    -1.50
     interacting
    -1.48
    Interaction
    -1.41
     interacted
    -1.29
     interacts
    -1.26
    interactions
    -1.23
    POSITIVE LOGITS
    OGND
    0.84
     with
    0.73
     Vikipedi
    0.67
    (!__
    0.64
     Tapatalk
    0.63
     Exactos
    0.63
    ⓘ
    0.59
     Asparagus
    0.57
     متعلقه
    0.55
    érons
    0.55
    Activations Density 0.465%

    No Known Activations