© 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. 4-CLT-HP
    7. 2525
    Prev
    Next
    INDEX
    Explanations

    do

    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
    StoreMessageInfo
    -0.72
     Elders
    -0.70
     photolibrary
    -0.68
     doubtnut
    -0.68
    /*
    -0.65
     gluon
    -0.63
    CppMethod
    -0.63
    󠁢
    -0.63
     pleaſure
    -0.63
    nically
    -0.61
    POSITIVE LOGITS
     who
    0.90
    who
    0.71
     cuyos
    0.67
     whose
    0.63
     cuyas
    0.60
     quien
    0.59
    whose
    0.58
     whom
    0.54
    whom
    0.52
    >",
    0.50
    Activations Density 0.003%

    No Known Activations