© 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. 5-CLT-HP
    7. 5010
    Prev
    Next
    INDEX
    Explanations

    creation building manufacturing (3 words)

    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
     <<<<<<<<<<<<<<
    -0.67
    出版年
    -0.66
    Personendaten
    -0.63
     continúas
    -0.58
    WriteAttribute
    -0.56
     commercially
    -0.55
    CloseOperation
    -0.53
    Easy
    -0.52
     popular
    -0.52
    initComponents
    -0.51
    POSITIVE LOGITS
    complexType
    0.71
    complexContent
    0.56
    buttonBar
    0.53
     virtual
    0.50
    hassee
    0.49
     getItemId
    0.49
    什么意思
    0.49
    __*/
    0.48
    virtual
    0.47
    IonicModule
    0.47
    Activations Density 0.003%

    No Known Activations