© 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. 20-CLT-HP
    7. 73097
    Prev
    Next
    INDEX
    Explanations

    hi

    np_max-act-logits · 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
    Билгалдахарш
    -0.67
    principalTable
    -0.65
     ***!
    -0.64
    writeFieldEnd
    -0.60
    TintMode
    -0.56
     <<<<<<<<<<<<<<
    -0.55
    setupUi
    -0.52
    habad
    -0.52
    pplung
    -0.50
    NOPQRST
    -0.50
    POSITIVE LOGITS
     esternos
    0.67
     street
    0.67
    street
    0.57
     streets
    0.56
    Street
    0.55
     spec
    0.53
    AccessorTable
    0.52
     Street
    0.52
    streets
    0.51
    HideFlags
    0.51
    Activations Density 0.000%

    No Known Activations