© 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. 42781
    Prev
    Next
    INDEX
    Explanations

    Medical/Injury 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
    Życiorys
    -0.51
    başı
    -0.48
     gradova
    -0.48
    __;
    -0.48
    elemField
    -0.47
    rzost
    -0.47
     necessárias
    -0.47
    tanleria
    -0.47
    onAttach
    -0.46
     Losses
    -0.46
    POSITIVE LOGITS
    duate
    0.63
    castic
    0.57
     versatile
    0.53
    NOSTIC
    0.53
    Bedankt
    0.52
    totic
    0.52
    ABLE
    0.52
    Atsauces
    0.51
    uxxxx
    0.50
    ytick
    0.50
    Activations Density 0.044%

    No Known Activations