© 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. 4-CLT-HP
    7. 809
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    identified
    -0.58
    suggested
    -0.56
    gapan
    -0.56
    urably
    -0.55
     Audiodateien
    -0.55
     Identified
    -0.54
     enviada
    -0.53
     identified
    -0.53
    discovered
    -0.53
    onix
    -0.52
    POSITIVE LOGITS
    tagHelperRunner
    0.60
    хьтан
    0.59
     BoxDecoration
    0.56
     HasFactory
    0.55
    GEBURTSDATUM
    0.51
    WriteTagHelper
    0.50
     reverb
    0.48
     Stew
    0.48
    setVerticalGroup
    0.46
    ItemLayout
    0.46
    Activations Density 0.000%

    No Known Activations