© 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. 0-CLT-HP
    7. 92077
    Prev
    Next
    INDEX
    Explanations

    young

    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
     surla
    -0.86
    ⓧ
    -0.82
     الحره
    -0.71
    ])));
    -0.69
    )}>
    -0.64
     상세
    -0.63
     dAtA
    -0.61
    UnsafeEnabled
    -0.61
     
    -0.61
     Réponses
    -0.60
    POSITIVE LOGITS
     children
    0.63
     adults
    0.62
     adulthood
    0.54
    CompleteListener
    0.52
    entieth
    0.51
     learners
    0.51
    sters
    0.50
    Comté
    0.48
     Australians
    0.48
     students
    0.48
    Activations Density 0.016%

    No Known Activations