© 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. 20-CLT-HP
    7. 72608
    Prev
    Next
    INDEX
    Explanations

    code/documentation

    np_max-act-logits · 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
     PropertyChanged
    -0.48
     nî
    -0.48
    hline
    -0.47
    ẵng
    -0.46
     verloren
    -0.43
     maxime
    -0.43
     violated
    -0.42
    ̤
    -0.42
     melang
    -0.42
     Priv
    -0.41
    POSITIVE LOGITS
    IsContent
    0.77
     createState
    0.73
    WriteTagHelper
    0.68
    Бахар
    0.65
     snippetHide
    0.55
    GMENT
    0.54
    djangoproject
    0.54
    Kaynakça
    0.54
     khảo
    0.54
    issenschaft
    0.54
    Activations Density 0.000%

    No Known Activations