© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42650
    Prev
    Next
    INDEX
    Explanations

    medical/scientific reports

    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
    abases
    -0.79
    abase
    -0.75
     Ruff
    -0.69
    utum
    -0.66
     itself
    -0.64
     nonatomic
    -0.56
    Ruff
    -0.55
    ruff
    -0.54
    itself
    -0.53
     himself
    -0.52
    POSITIVE LOGITS
    tagHelperRunner
    0.66
     <<<<<<<<<<<<<<
    0.59
    featureID
    0.56
    θεια
    0.56
    Hozzáférés
    0.54
     bezeichneter
    0.54
    مصادر
    0.53
    dings
    0.53
     Segel
    0.52
    مراجع
    0.52
    Activations Density 0.044%

    No Known Activations