© 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. 97235
    Prev
    Next
    INDEX
    Explanations

    Could not determine pattern.under

    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
     Carroll
    -0.52
    createServer
    -0.49
    TagHelper
    -0.48
     lạc
    -0.48
    شو
    -0.48
     assets
    -0.48
     versa
    -0.46
     podjet
    -0.46
    onite
    -0.45
     former
    -0.44
    POSITIVE LOGITS
     <=",
    0.73
    RegressionTest
    0.69
    gameserver
    0.68
    tvguidetime
    0.66
     ddelweddau
    0.59
    ThroughAttribute
    0.59
    TemporalType
    0.57
    RTEX
    0.56
    :✨
    0.55
    AndEndTag
    0.54
    Activations Density 0.004%

    No Known Activations