© 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. 97028
    Prev
    Next
    INDEX
    Explanations

    production/manufacture

    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
     <<<<<<<<<<<<<<
    -0.69
    __(/*!
    -0.67
    necedor
    -0.61
    NUMX
    -0.59
    DockStyle
    -0.59
    ├──
    -0.57
    
    -0.57
    RectangleBorder
    -0.56
    berdayakan
    -0.56
     Pardavimas
    -0.56
    POSITIVE LOGITS
    .
    0.53
    HttpDelete
    0.48
     tuturor
    0.48
    ngiliz
    0.47
     in
    0.42
    ban
    0.42
     stab
    0.41
     equilibria
    0.41
    log
    0.40
     finishes
    0.40
    Activations Density 0.010%

    No Known Activations