© 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. 4-CLT-HP
    7. 1268
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
     GenerationType
    -0.60
    thodoxy
    -0.51
     AssemblyProduct
    -0.49
    TagMode
    -0.48
     RECORD
    -0.48
     Italijanski
    -0.47
    flink
    -0.47
    Bulb
    -0.46
     referenties
    -0.46
     pageContext
    -0.45
    POSITIVE LOGITS
    AccessorTable
    0.61
     دیکھیے
    0.60
    __*/
    0.60
     Athenians
    0.56
     tartalomajánló
    0.52
    fycat
    0.52
     Mongolian
    0.52
    principalTable
    0.51
     Yankee
    0.51
     AssemblyVersion
    0.51
    Activations Density 0.008%

    No Known Activations