© 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. 38287
    Prev
    Next
    INDEX
    Explanations

    building

    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
     building
    -1.76
    building
    -1.46
    Building
    -1.41
     build
    -1.37
     BUILDING
    -1.30
     Building
    -1.27
    BUILDING
    -1.23
    build
    -1.16
     Build
    -1.13
     builds
    -1.11
    POSITIVE LOGITS
     flanges
    0.65
     NDEBUG
    0.62
     defaultstate
    0.61
     admixture
    0.61
    ControllerAdvice
    0.60
    ResumeLayout
    0.59
     trays
    0.59
     flange
    0.59
     PPA
    0.56
     airbags
    0.55
    Activations Density 0.256%

    No Known Activations