© 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. 20-CLT-HP
    7. 73284
    Prev
    Next
    INDEX
    Explanations

    Technical/formal writing

    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
     Audiodateien
    -0.64
     PopupWindow
    -0.58
    SBATCH
    -0.57
    بوابة
    -0.57
     مرئيه
    -0.57
    SizeF
    -0.56
    StartTag
    -0.55
    AndEndTag
    -0.55
     الدولى
    -0.54
     GetEnumerator
    -0.52
    POSITIVE LOGITS
    l
    0.71
     l
    0.59
    lli
    0.57
    L
    0.57
     mer
    0.54
    ls
    0.53
     L
    0.53
     Mer
    0.49
     lx
    0.49
     lungs
    0.48
    Activations Density 0.000%

    No Known Activations