© 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. 1-CLT-HP
    7. 13175
    Prev
    Next
    INDEX
    Explanations

    medical topics

    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
    DockStyle
    -0.46
    CWE
    -0.45
    Directions
    -0.44
    こそ
    -0.44
     ADMINISTRATION
    -0.40
     Among
    -0.40
     Unless
    -0.39
    aad
    -0.39
    Among
    -0.39
     дописавши
    -0.39
    POSITIVE LOGITS
     دیکھیے
    0.93
     iſt
    0.77
     themſelves
    0.76
     Eſ
    0.69
     fhew
    0.69
     Efq
    0.68
     purpoſe
    0.68
     anſ
    0.67
     himſelf
    0.66
    SqlClient
    0.66
    Activations Density 0.095%

    No Known Activations