© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3039
    Prev
    Next
    INDEX
    Explanations

    Code errors/debugging

    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
    RegressionTest
    -0.68
    juries
    -0.61
     betweenstory
    -0.60
     désolés
    -0.60
    manship
    -0.59
    //
    -0.59
    Demografie
    -0.57
    transQ
    -0.56
    syms
    -0.56
    QUADS
    -0.55
    POSITIVE LOGITS
     beginnetje
    0.57
    WebVitals
    0.52
     stater
    0.46
    adə
    0.45
     مشين
    0.45
    Tikang
    0.44
    ByDefault
    0.41
    imply
    0.40
    Geplaatst
    0.39
    hoeddwyd
    0.39
    Activations Density 0.081%

    No Known Activations