© 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. 3
    Prev
    Next
    INDEX
    Explanations

    the word "and"

    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
     ftate
    -0.82
     Aton
    -0.77
     fubject
    -0.74
     poffible
    -0.74
     Whigs
    -0.73
     caufe
    -0.73
     Jefus
    -0.73
     Efq
    -0.73
     Athenians
    -0.71
     Shakspeare
    -0.71
    POSITIVE LOGITS
     and
    2.16
     AND
    1.63
     And
    1.60
     và
    1.55
    and
    1.47
     \&
    1.41
     и
    1.36
    และ
    1.34
     και
    1.31
    그리고
    1.30
    Activations Density 3.841%

    No Known Activations