© 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. 5-CLT-HP
    7. 91619
    Prev
    Next
    INDEX
    Explanations

    scientific/math formulas

    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
    ela
    -0.51
    تفصیلات
    -0.51
     géneros
    -0.50
    el
    -0.50
     AssemblyTitle
    -0.49
    poti
    -0.49
    np
    -0.48
    peño
    -0.47
    rahat
    -0.47
    ReusableCell
    -0.46
    POSITIVE LOGITS
    RectangleBorder
    0.59
    colnshire
    0.56
     geometry
    0.55
     ProtoMessage
    0.54
    tvguidetime
    0.53
     Gea
    0.53
    mappedBy
    0.52
    Geplaatst
    0.52
    uxxxx
    0.52
     backgrounds
    0.52
    Activations Density 0.002%

    No Known Activations