© 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. 0-CLT-HP
    7. 43888
    Prev
    Next
    INDEX
    Explanations

    tubing

    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
    network
    -0.94
     network
    -0.84
    cology
    -0.65
    entially
    -0.63
    natal
    -0.62
     Roskov
    -0.62
    ParallelGroup
    -0.60
    bilis
    -0.60
    Network
    -0.59
    shaft
    -0.59
    POSITIVE LOGITS
    NameInMap
    0.62
     protoimpl
    0.56
     saites
    0.56
     obie
    0.56
     esetben
    0.54
    NewReader
    0.54
     superseded
    0.54
     yoktur
    0.52
    p
    0.52
    i
    0.52
    Activations Density 1.086%

    No Known Activations