© 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. 93385
    Prev
    Next
    INDEX
    Explanations

    process

    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
    SPATH
    -0.78
    ariste
    -0.63
    OGND
    -0.60
    gean
    -0.60
    oque
    -0.59
     виправивши
    -0.59
    lucene
    -0.57
    графия
    -0.57
    графія
    -0.57
    SBS
    -0.56
    POSITIVE LOGITS
     poitrine
    0.54
     Pues
    0.52
     processing
    0.50
    processing
    0.49
     surmounted
    0.48
    processed
    0.48
    :✨
    0.48
     Estudi
    0.47
     Ahnung
    0.47
     Tenga
    0.47
    Activations Density 0.014%

    No Known Activations