© 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. 0-RES-MATRYOSHKA-DC
    7. 11207
    Prev
    Next
    INDEX
    Explanations

    sequences of characters indicating hexadecimal color codes or similar patterns

    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
    \#
    -1.45
    \%
    -1.43
     \#
    -1.41
    \$
    -1.22
    \%)
    -1.10
     \$
    -1.07
    \'
    -1.06
    \%,
    -0.97
     \%
    -0.96
     $\$
    -0.96
    POSITIVE LOGITS
    \|_{
    0.72
    \|_{\
    0.71
    ).__
    0.69
     _
    0.69
    aarrggbb
    0.68
    <sub>
    0.66
     _,
    0.65
    webElement
    0.65
    —
    0.65
    ————————
    0.62
    Activations Density 0.008%

    No Known Activations