© 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. 94048
    Prev
    Next
    INDEX
    Explanations

    Topics

    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
    AsyncResult
    -0.62
     الحره
    -0.61
    enumi
    -0.55
    ISupport
    -0.53
    AccessorTable
    -0.52
    ArrowToggle
    -0.52
    AndEndTag
    -0.52
    ever
    -0.51
    mb
    -0.50
     Topics
    -0.50
    POSITIVE LOGITS
    ubakar
    0.52
    roek
    0.52
    icoot
    0.51
    HOLDER
    0.51
    dflare
    0.51
    intrag
    0.50
    dzić
    0.50
    waran
    0.50
     disponibilités
    0.49
    ukah
    0.49
    Activations Density 0.721%

    No Known Activations