© 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. 0-CLT-HP
    7. 40048
    Prev
    Next
    INDEX
    Explanations

    anatomical location

    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
     posterior
    -1.14
     anterior
    -1.04
     facility
    -1.03
     facilities
    -0.97
    facility
    -0.90
     Posterior
    -0.88
     Anterior
    -0.83
    facilities
    -0.78
     Facility
    -0.77
    Facility
    -0.69
    POSITIVE LOGITS
    MigrationBuilder
    0.66
    itized
    0.65
    PyExc
    0.61
    ized
    0.59
     kasarigan
    0.57
    ization
    0.55
    (");
    0.55
    хьтан
    0.53
    CodeAttribute
    0.52
    ize
    0.50
    Activations Density 0.439%

    No Known Activations