© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9392
    Prev
    Next
    INDEX
    Explanations

    factories, manufacturing plants

    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
    uer
    -1.09
    NameInMap
    -0.73
    曖昧さ回避
    -0.69
    ReusableCell
    -0.65
    WireFormatLite
    -0.63
    PreInfinity
    -0.60
    gridy
    -0.59
     onAnimation
    -0.58
     Vries
    -0.57
    blurRadius
    -0.57
    POSITIVE LOGITS
     zus
    0.46
     Histórico
    0.45
    YOUR
    0.44
    esgue
    0.42
    INSEE
    0.41
    BagLayout
    0.41
    fortawesome
    0.41
     yours
    0.40
    $_['
    0.40
    rån
    0.40
    Activations Density 0.029%

    No Known Activations