© 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. 4-CLT-HP
    7. 1155
    Prev
    Next
    INDEX
    Explanations

    be

    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
    ViewFeatures
    -0.79
    AndEndTag
    -0.70
    IVEREF
    -0.64
    Démographie
    -0.62
    providedIn
    -0.60
    انيف
    -0.58
     اللا
    -0.55
    Према
    -0.55
    تقاوى
    -0.54
    yship
    -0.54
    POSITIVE LOGITS
     argued
    0.52
    ündigung
    0.52
     odkazy
    0.50
     predicted
    0.49
     cheaply
    0.48
    <_>
    0.47
     calculated
    0.47
     varied
    0.45
     inferred
    0.44
     reasoned
    0.44
    Activations Density 0.004%

    No Known Activations