© 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. 5-CLT-HP
    7. 4076
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    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
     happened
    -0.59
     happening
    -0.58
    happened
    -0.51
     occurring
    -0.48
     ocur
    -0.47
     occurred
    -0.47
    prehensive
    -0.46
    WithMany
    -0.46
    happens
    -0.45
     Happened
    -0.45
    POSITIVE LOGITS
    ValueStyle
    0.90
     propOrder
    0.81
    parsedMessage
    0.79
     utafitiHapana
    0.78
     &___
    0.71
    WebElementEntity
    0.71
    EndGlobalSection
    0.71
    DockStyle
    0.71
     pinulongan
    0.70
    AndEndTag
    0.70
    Activations Density 0.004%

    No Known Activations