© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93178
    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
     réguli
    -0.94
    berdayakan
    -0.92
     ainfi
    -0.84
     varandra
    -0.83
     originais
    -0.82
     roulant
    -0.82
     متعلقه
    -0.82
    Preparazione
    -0.82
     genoux
    -0.81
     complètes
    -0.81
    POSITIVE LOGITS
    ist
    0.77
     Ob
    0.59
    er
    0.59
    rol
    0.58
    ity
    0.57
    ese
    0.56
    ob
    0.55
     V
    0.53
     non
    0.52
    ism
    0.52
    Activations Density 0.069%

    No Known Activations