© 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. 4-CLT-HP
    7. 586
    Prev
    Next
    INDEX
    Explanations

    no

    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
    modelBuilder
    -0.63
     CYTHON
    -0.60
     kasarigan
    -0.60
    󠁿
    -0.58
    labus
    -0.54
    vantaged
    -0.53
    protoimpl
    -0.53
    כך
    -0.53
    gico
    -0.53
    tagHelperRunner
    -0.53
    POSITIVE LOGITS
    sizeCache
    0.73
     regard
    0.59
    kháu
    0.56
     modifications
    0.55
    autoreleasepool
    0.55
    řev
    0.53
     or
    0.52
     loss
    0.51
     reduction
    0.50
     need
    0.50
    Activations Density 0.007%

    No Known Activations