© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11374
    Prev
    Next
    INDEX
    Explanations

    overhanging

    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
     betweenstory
    -0.84
     Baillargeon
    -0.70
    JspWriter
    -0.60
     ویکی‌پدی
    -0.60
     Italijani
    -0.60
    TagMode
    -0.59
     AssemblyTitle
    -0.59
     <<<<<<<<<<<<<<
    -0.56
     jadx
    -0.56
    parsedMessage
    -0.56
    POSITIVE LOGITS
    AnimationsModule
    0.59
    reness
    0.53
    rets
    0.48
    ience
    0.47
    eners
    0.46
     debout
    0.45
    ResourceManager
    0.45
    retty
    0.44
    reactstrap
    0.43
    nehmen
    0.43
    Activations Density 0.104%

    No Known Activations