© 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. 5-CLT-HP
    7. 2132
    Prev
    Next
    INDEX
    Explanations

    possessive 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
     propio
    -0.54
     own
    -0.49
    Own
    -0.46
    自身の
    -0.44
    יצוני
    -0.44
     bodily
    -0.44
    рыв
    -0.43
    τυχ
    -0.43
    com
    -0.42
     propia
    -0.42
    POSITIVE LOGITS
    oredCriteria
    0.68
    DockStyle
    0.63
     <=",
    0.62
    StoryboardSegue
    0.62
     generation
    0.62
     or
    0.60
    extAlignment
    0.59
    MessageState
    0.58
     generazione
    0.57
     timeType
    0.57
    Activations Density 0.002%

    No Known Activations