© 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. 1-CLT-HP
    7. 15253
    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
     referenties
    -0.74
     Wikiseite
    -0.58
     AppCompatTheme
    -0.57
     quelconque
    -0.54
     tenisky
    -0.54
     StatefulWidget
    -0.53
    beeld
    -0.52
     indietro
    -0.52
     DIEGO
    -0.52
     Title
    -0.52
    POSITIVE LOGITS
     kaynağından
    0.58
     himself
    0.55
     themselves
    0.54
     herself
    0.53
     myself
    0.50
    itemBuilder
    0.49
     ourselves
    0.48
    ">//
    0.46
    setDo
    0.46
    DockStyle
    0.45
    Activations Density 0.013%

    No Known Activations