© 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. 1027
    Prev
    Next
    INDEX
    Explanations

    references to corporate entities or formal organizational designations

    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
    parsedMessage
    -0.62
    UnusedPrivate
    -0.61
     >=",
    -0.61
     ***!
    -0.57
    cstr
    -0.56
     }}"></
    -0.55
    csname
    -0.54
    UTED
    -0.54
    ]**
    -0.53
    MessageOf
    -0.53
    POSITIVE LOGITS
     Inc
    4.63
    Inc
    4.03
     INC
    3.52
    inc
    3.33
     inc
    3.31
    INC
    2.72
     Incorporated
    2.69
     LLC
    2.14
     Ltd
    1.91
     INCORPOR
    1.78
    Activations Density 0.224%

    No Known Activations