© 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. 6752
    Prev
    Next
    INDEX
    Explanations

    references to scientific journals or publications

    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
    Rev
    -0.93
     Rev
    -0.91
     rev
    -0.73
    rev
    -0.71
    REV
    -0.59
     REV
    -0.58
     kaarangay
    -0.56
     Besoin
    -0.54
    <bos>
    -0.54
    WithIOException
    -0.54
    POSITIVE LOGITS
     Lett
    3.59
    Lett
    3.52
     Letters
    2.17
     LETTERS
    1.96
     letters
    1.81
    Letters
    1.80
    LETTERS
    1.63
    letters
    1.62
     Letter
    1.61
     letter
    1.59
    Activations Density 0.002%

    No Known Activations