Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12644
    Prev
    Next
    INDEX
    Explanations

    reflexive 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
     varandra
    -0.89
     enfans
    -0.85
     zelve
    -0.83
     itſelf
    -0.80
     avoient
    -0.76
     voisins
    -0.69
     themſelves
    -0.69
     pauvres
    -0.68
     auroit
    -0.66
     alluminio
    -0.66
    POSITIVE LOGITS
    "}>
    0.54
    ')['
    0.54
    });*/
    0.53
    })*/
    0.52
     ?>">
    0.51
    ]}>
    0.51
    =!
    0.50
    .');
    0.50
     stand
    0.50
    ()}>
    0.49
    Activations Density 0.025%

    No Known Activations