© 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. 91961
    Prev
    Next
    INDEX
    Explanations

    academic/medical research

    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
     ujednoznacz
    -0.90
    Rohy
    -0.72
    Autoritní
    -0.65
     تانيه
    -0.64
     TextInputType
    -0.64
     "..\..\..\
    -0.64
     Administrativna
    -0.63
    ian
    -0.62
     speciality
    -0.62
     "..\..\
    -0.61
    POSITIVE LOGITS
     of
    0.95
     ofthe
    0.51
     setting
    0.50
    ing
    0.46
    lahir
    0.46
     in
    0.45
    tiqueta
    0.45
     put
    0.45
     holder
    0.45
     is
    0.44
    Activations Density 0.417%

    No Known Activations