© 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. 1268
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    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
     act
    -1.26
    act
    -1.09
    matter
    -1.06
     matter
    -1.05
    acts
    -0.93
     acts
    -0.85
     matters
    -0.77
    Acting
    -0.74
    ACT
    -0.73
     Act
    -0.73
    POSITIVE LOGITS
     مرئيه
    0.70
    +#+#
    0.64
    gdala
    0.61
     mercies
    0.59
    CloseOperation
    0.59
    ValueStyle
    0.54
     bequeathed
    0.54
    
    0.53
     дописавши
    0.52
    endregion
    0.51
    Activations Density 0.210%

    No Known Activations