© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 480
    Prev
    Next
    INDEX
    Explanations

    Heath

    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
     Heath
    -0.84
    Heath
    -0.78
    heath
    -0.69
     تضيفلها
    -0.63
     sanitaires
    -0.55
     fournis
    -0.49
     scolaires
    -0.44
    Health
    -0.44
     amélior
    -0.43
     heath
    -0.43
    POSITIVE LOGITS
     purpoſe
    0.90
     itſelf
    0.90
     ſta
    0.87
     ſte
    0.82
     myſelf
    0.81
     raiſ
    0.79
     fevere
    0.77
     faſt
    0.76
    oa̍t
    0.75
     Reſ
    0.75
    Activations Density 0.039%

    No Known Activations