© 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. 105
    Prev
    Next
    INDEX
    Explanations

    the word "of" with varying degrees of activation, sometimes alongside other words

    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
    uerre
    -0.56
    issau
    -0.54
    зар
    -0.51
    ;
    -0.51
    вят
    -0.50
     renunci
    -0.50
     écrite
    -0.50
     Orrell
    -0.49
     Obrigado
    -0.48
    kingen
    -0.47
    POSITIVE LOGITS
     of
    1.85
     OF
    1.38
     Of
    1.20
    .)}
    1.18
    of
    1.17
     của
    1.17
     BoxDecoration
    1.14
    オブ
    1.11
    Of
    1.09
     ของ
    1.08
    Activations Density 4.377%

    No Known Activations