© 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. 6919
    Prev
    Next
    INDEX
    Explanations

    references to quotation marks or quotation-like symbols

    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
    rikes
    -0.66
    GHIJKLM
    -0.64
    openzeppelin
    -0.63
    adə
    -0.63
    uoco
    -0.63
    yenne
    -0.59
    PRESA
    -0.59
    UELA
    -0.59
    őle
    -0.58
    formin
    -0.57
    POSITIVE LOGITS
    "}},
    0.59
     *>
    0.58
    ConstraintMaker
    0.57
    }}},
    0.56
     ***!
    0.56
    useEffect
    0.53
    Hochspringen
    0.52
     }}}{
    0.52
     }>
    0.51
    Skocz
    0.51
    Activations Density 0.171%

    No Known Activations