© 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
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 3020
    Prev
    Next
    INDEX
    Explanations

    references to the word "on" used as an indicator of emphasis or importance

    oai_token-act-pair · gpt-4.1-nano
    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
    TONE
    -0.71
    ✨:
    -0.71
    gesellschaft
    -0.69
    DockStyle
    -0.68
     Meksiku
    -0.67
     ویکی‌پدی
    -0.66
    توض
    -0.66
     ModelExpression
    -0.66
    IONI
    -0.65
    jsii
    -0.65
    POSITIVE LOGITS
    on
    2.64
    ON
    1.82
    On
    0.72
    at
    0.70
    onlu
    0.70
    in
    0.69
    onka
    0.68
    onné
    0.68
    onner
    0.67
    onan
    0.65
    Activations Density 0.082%

    No Known Activations