© 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. 5-CLT-HP
    4. 94575
    Prev
    Next
    INDEX
    Explanations

    descriptive text

    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
     been
    -0.67
    ,
    -0.58
    insee
    -0.52
     dehydration
    -0.49
     Архів
    -0.45
     to
    -0.44
    Formik
    -0.44
     Wikimédia
    -0.44
    ษา
    -0.43
     doświad
    -0.43
    POSITIVE LOGITS
    PreferredItem
    0.71
     الرياضيه
    0.66
    بوابة
    0.66
    IntoConstraints
    0.66
    MLLoader
    0.65
    AndEndTag
    0.63
    KommentareTeilen
    0.63
    HostException
    0.61
     MonoBehaviour
    0.60
    ']))
    
    0.60
    Activations Density 0.001%

    No Known Activations