© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13668
    Prev
    Next
    INDEX
    Explanations

    analytical

    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
     pinulongan
    -0.63
     Ayu
    -0.53
     Marquette
    -0.52
    INTE
    -0.52
    ruta
    -0.51
    RectangleBorder
    -0.51
     Sana
    -0.50
    sene
    -0.49
    repl
    -0.49
     Stare
    -0.49
    POSITIVE LOGITS
    principalTable
    0.70
     invokingState
    0.68
    ist
    0.68
    InjectAttribute
    0.59
    GEBURTS
    0.59
    ists
    0.57
    RegressionTest
    0.56
    principalColumn
    0.56
    featureID
    0.55
     NUKAT
    0.54
    Activations Density 0.066%

    No Known Activations