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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2818
    Prev
    Next
    INDEX
    Explanations

    medical/physical ailments

    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
    bindingNavigator
    -0.57
    TemporalType
    -0.54
    BitConverter
    -0.53
     تانيه
    -0.52
    mappedBy
    -0.49
    ThroughAttribute
    -0.48
     rehabilitate
    -0.47
     Climatic
    -0.45
     doInBackground
    -0.44
     fixation
    -0.44
    POSITIVE LOGITS
     of
    0.73
    CppMethod
    0.70
    mybatisplus
    0.62
    hdashline
    0.56
    rego
    0.55
     such
    0.54
    róleo
    0.52
    encies
    0.51
    tivities
    0.51
    sima
    0.51
    Activations Density 0.001%

    No Known Activations