© 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. 3914
    Prev
    Next
    INDEX
    Explanations

    repeated pattern of a specific message prefix, indicating it detects the presence of a signaling or status message

    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
     IERC
    -0.72
    Datuak
    -0.69
     مرئيه
    -0.67
     /\.
    -0.66
    RestController
    -0.65
    lahoma
    -0.64
    tagext
    -0.64
    iastes
    -0.64
     Wyoming
    -0.63
    UITextField
    -0.61
    POSITIVE LOGITS
     RT
    2.91
    RT
    2.88
     rt
    1.91
    rt
    1.91
    Rt
    1.42
     Rt
    1.23
    rts
    1.21
     RTV
    1.10
    RTN
    1.03
     RTE
    0.99
    Activations Density 0.015%

    No Known Activations