© 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. 362
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people

    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
     NSCoder
    -0.91
    IsMutable
    -0.91
    SharedDtor
    -0.83
    Personendaten
    -0.79
    GEBURTSDATUM
    -0.79
     متعلقه
    -0.77
    TagMode
    -0.77
    mobileqq
    -0.75
    StructEnd
    -0.73
     חיצוניים
    -0.73
    POSITIVE LOGITS
    andle
    0.40
    endphp
    0.40
     my
    0.39
    </i>
    0.39
     myself
    0.39
    and
    0.38
    ↵↵
    0.38
    طوب
    0.38
    ouse
    0.37
     personally
    0.37
    Activations Density 0.007%

    No Known Activations