© 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. 97984
    Prev
    Next
    INDEX
    Explanations

    next

    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
     originally
    -0.45
     initially
    -0.43
     pred
    -0.41
    pha
    -0.40
     BRE
    -0.40
     early
    -0.39
     hard
    -0.37
     Around
    -0.37
     originalmente
    -0.37
     origin
    -0.36
    POSITIVE LOGITS
     Normdatei
    1.03
    tagHelperRunner
    0.93
     betweenstory
    0.89
    richTextPanel
    0.86
     الرياضيه
    0.82
     ***!
    0.80
    WebElementEntity
    0.79
    abestanden
    0.79
     kasarigan
    0.78
    TintMode
    0.77
    Activations Density 0.003%

    No Known Activations