© 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. 679
    Prev
    Next
    INDEX
    Explanations

    businesses

    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
    BeginContext
    -0.65
    "]];
    -0.60
     thicknesses
    -0.58
     glories
    -0.55
    ']],
    -0.55
     Ignorance
    -0.54
    DialogComponent
    -0.54
     Penetration
    -0.53
     thickness
    -0.52
    SZ
    -0.50
    POSITIVE LOGITS
     like
    1.13
     such
    0.82
     propOrder
    0.79
    像是
    0.71
     kuten
    0.71
     including
    0.71
     need
    0.66
    RegressionTest
    0.65
     across
    0.65
     "..\..\
    0.64
    Activations Density 0.000%

    No Known Activations