© 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. 3041
    Prev
    Next
    INDEX
    Explanations

    together

    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
    Ps
    -0.59
    We
    -0.59
     nostru
    -0.57
    Thus
    -0.56
    You
    -0.55
    jectable
    -0.54
     يتيمه
    -0.54
    But
    -0.52
     Accordingly
    -0.52
    شاف
    -0.51
    POSITIVE LOGITS
     they
    1.06
     he
    0.60
     mereka
    0.60
     them
    0.57
     They
    0.56
     @"/
    0.54
     они
    0.54
    他们
    0.54
    they
    0.53
     Waray
    0.53
    Activations Density 0.001%

    No Known Activations