© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38528
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     “
    -1.02
     "
    -1.02
     new
    -0.91
     the
    -0.90
     a
    -0.85
     just
    -0.85
     one
    -0.83
     no
    -0.82
     all
    -0.82
     real
    -0.80
    POSITIVE LOGITS
    They
    1.01
     avoient
    0.98
    <bos>
    0.98
     étoient
    0.97
     vectorielles
    0.89
     démocr
    0.88
     fermés
    0.88
     pouvoit
    0.86
     feroit
    0.86
     étoit
    0.85
    Activations Density 0.134%

    No Known Activations