© 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. 20-CLT-HP
    7. 76948
    Prev
    Next
    INDEX
    Explanations

    Medical or chemical contexts

    np_max-act-logits · 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
    ed
    -0.85
    et
    -0.64
    iel
    -0.59
    iv
    -0.57
    e
    -0.56
    ib
    -0.56
    email
    -0.54
    ei
    -0.54
    ire
    -0.53
    ian
    -0.52
    POSITIVE LOGITS
    uminescence
    0.59
     mouseY
    0.55
    inity
    0.53
    ator
    0.53
    omics
    0.52
     متعلقه
    0.50
    astic
    0.50
    atory
    0.50
    umt
    0.49
    ysis
    0.47
    Activations Density 0.017%

    No Known Activations