© 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. 0-CLT-HP
    4. 92580
    Prev
    Next
    INDEX
    Explanations

    materials/properties

    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
     enfans
    -1.19
     plufieurs
    -1.08
     myſelf
    -1.05
     détru
    -1.04
     ainfi
    -1.04
     étrangère
    -1.02
     prêtres
    -1.02
     touristes
    -1.00
     decorazione
    -1.00
     dieux
    -0.99
    POSITIVE LOGITS
     and
    0.64
    .
    0.58
     products
    0.56
    ,
    0.55
     (
    0.53
     to
    0.50
    ↵
    0.47
     product
    0.47
    ↵↵
    0.47
     with
    0.46
    Activations Density 0.063%

    No Known Activations