© 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. 1-RES-MATRYOSHKA-DC
    7. 126
    Prev
    Next
    INDEX
    Explanations

    expressions of technical or scientific concepts, often involving specialized terminology and 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
    ReusableCell
    -0.54
    IKAN
    -0.44
    igshid
    -0.44
    minist
    -0.43
    λαν
    -0.43
    IMON
    -0.43
    disambiguation
    -0.43
     exception
    -0.42
    zola
    -0.42
     Tent
    -0.42
    POSITIVE LOGITS
    <bos>
    3.33
     itſelf
    0.80
     raiſ
    0.70
    /*
    0.69
    /**
    0.66
     myſelf
    0.63
    __':
    0.62
    #
    0.61
    //
    0.57
     Monfieur
    0.57
    Activations Density 98.582%

    No Known Activations