© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12147
    Prev
    Next
    INDEX
    Explanations

    um

    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
    um
    -0.69
    UM
    -0.54
    umia
    -0.48
    LLocation
    -0.47
    umat
    -0.47
     líqu
    -0.46
    minis
    -0.45
    name
    -0.45
     käns
    -0.44
    umą
    -0.44
    POSITIVE LOGITS
     ivelany
    0.70
    }\]
    0.69
    addCriterion
    0.69
     متعلقه
    0.68
     Wicidata
    0.68
    disposing
    0.67
     actionMode
    0.65
    MigrationBuilder
    0.62
    principalColumn
    0.62
     Autorisations
    0.62
    Activations Density 0.011%

    No Known Activations