© 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. 1-CLT-HP
    7. 15252
    Prev
    Next
    INDEX
    Explanations

    sideways

    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
     AssemblyCulture
    -0.72
    IUrlHelper
    -0.71
     CTC
    -0.63
    ChildScrollView
    -0.62
    numerusform
    -0.62
    ftagPool
    -0.62
    contentLoaded
    -0.58
    WebMethod
    -0.54
    DBNull
    -0.54
    thâu
    -0.53
    POSITIVE LOGITS
    mogorov
    0.50
    nye
    0.48
    ly
    0.47
    了
    0.46
    mee
    0.46
    meri
    0.46
    weeted
    0.45
    :✨
    0.45
    Rigidbody
    0.44
     rêves
    0.44
    Activations Density 0.028%

    No Known Activations