© 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. 41858
    Prev
    Next
    INDEX
    Explanations

    Medical/technical 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
    s
    -0.70
     démocr
    -0.65
    varying
    -0.59
    schmidt
    -0.58
    pheric
    -0.53
    ography
    -0.53
     között
    -0.52
    enius
    -0.52
    ynthetic
    -0.51
    Abend
    -0.49
    POSITIVE LOGITS
     Efq
    0.71
    contentLoaded
    0.64
    Sucesor
    0.61
     Patro
    0.61
     myſelf
    0.59
     iſt
    0.58
     fevere
    0.58
     firewood
    0.57
    -};
    0.57
     uſed
    0.56
    Activations Density 0.118%

    No Known Activations