© 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. 97890
    Prev
    Next
    INDEX
    Explanations

    reserve

    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
    +#+#
    -0.69
     calendriers
    -0.62
    liothèque
    -0.59
    HEY
    -0.55
    SequentialGroup
    -0.55
     heifers
    -0.54
     sáb
    -0.54
     gema
    -0.53
    bootstrapcdn
    -0.53
    ValueStyle
    -0.53
    POSITIVE LOGITS
     word
    0.60
    Przypisy
    0.56
     words
    0.56
     &___
    0.56
    word
    0.49
    complexContent
    0.49
     Words
    0.48
    bukkit
    0.47
     QLabel
    0.46
     Jurí
    0.45
    Activations Density 0.003%

    No Known Activations