© 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. 1098
    Prev
    Next
    INDEX
    Explanations

    hyperbaric and medical contexts

    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
    cisi
    -0.64
    baric
    -0.63
     Catawiki
    -0.51
    inder
    -0.49
    renewcommand
    -0.49
    präsident
    -0.49
     NSCoder
    -0.49
    aure
    -0.48
    mahami
    -0.46
     Squal
    -0.45
    POSITIVE LOGITS
    __":
    0.66
    ----</
    0.65
    kuuta
    0.56
    taza
    0.52
    axel
    0.52
    cases
    0.51
    __":
    0.51
    edded
    0.51
    order
    0.50
     intptr
    0.50
    Activations Density 0.016%

    No Known Activations