© 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. 5023
    Prev
    Next
    INDEX
    Explanations

    building levels and floors

    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
     disparu
    -0.41
    attached
    -0.41
     betweenstory
    -0.40
     namanya
    -0.40
    FunctionFlags
    -0.40
     Zubehör
    -0.39
     communiquer
    -0.39
    >
    -0.39
     abstrait
    -0.39
     heureux
    -0.38
    POSITIVE LOGITS
     NgModule
    0.76
    Hentet
    0.64
     useStyles
    0.61
    хь
    0.60
    NgModule
    0.59
    awtextra
    0.58
    MessageWindow
    0.57
    Obrázky
    0.57
     level
    0.57
     protoimpl
    0.56
    Activations Density 0.001%

    No Known Activations