© 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. 1-CLT-HP
    7. 700
    Prev
    Next
    INDEX
    Explanations

    names

    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
     Marian
    -1.05
     Marion
    -0.98
    Marion
    -0.91
    Marian
    -0.85
     maria
    -0.82
     Maria
    -0.80
     Mariano
    -0.78
    marin
    -0.77
    Maria
    -0.77
     mariana
    -0.75
    POSITIVE LOGITS
    spiegel
    0.57
    PerformLayout
    0.55
    cho
    0.52
    et
    0.49
    ett
    0.49
    aarrggbb
    0.49
    ety
    0.49
    gt
    0.49
    GT
    0.48
    ADELPHIA
    0.48
    Activations Density 0.011%

    No Known Activations