© 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
    2. Gemma-2-2B
    3. 3-RES-MATRYOSHKA-DC
    4. 88
    Prev
    Next
    INDEX
    Explanations

    the word "but" or it's foreign equivalent

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.90
     Efq
    -0.88
     Jefus
    -0.87
     crdi
    -0.84
     Majefty
    -0.83
     Shakspeare
    -0.82
     himſelf
    -0.78
     Tacitus
    -0.77
     Cæsar
    -0.77
     Croydon
    -0.77
    POSITIVE LOGITS
     but
    2.58
     But
    2.53
    but
    2.25
    But
    2.25
     BUT
    2.05
     pero
    1.90
     nhưng
    1.73
    BUT
    1.72
    但
    1.66
     tetapi
    1.64
    Activations Density 3.028%

    No Known Activations