© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90835
    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
    Negative Logits
    <bos>
    -0.47
    ol
    -0.47
     breathes
    -0.45
    ίσ
    -0.43
    last
    -0.43
    Slf
    -0.42
     disponibilités
    -0.41
     vesti
    -0.41
    })));
    -0.41
    diğimiz
    -0.41
    POSITIVE LOGITS
     expertise
    0.70
    expertise
    0.64
     насељу
    0.63
     $_"
    0.63
    Atsauces
    0.62
    ViewFeatures
    0.59
     interesses
    0.59
     ferdig
    0.58
     rootReducer
    0.58
     Audiodateien
    0.58
    Activations Density 0.000%

    No Known Activations