© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46222
    Prev
    Next
    INDEX
    Explanations

    Medical/scientific literature

    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
    atosis
    -0.74
    abi
    -0.69
     Савезне
    -0.56
    issa
    -0.56
     Suicide
    -0.53
     Infinity
    -0.52
    Mab
    -0.52
    makeConstraints
    -0.51
    Infinity
    -0.50
     LUMP
    -0.49
    POSITIVE LOGITS
     CWE
    0.60
     plads
    0.58
    reszcie
    0.58
     AssemblyCulture
    0.54
    thren
    0.54
     nahilalakip
    0.53
     rigtig
    0.52
    zeiro
    0.52
     legno
    0.51
     métiers
    0.51
    Activations Density 0.008%

    No Known Activations