© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13182
    Prev
    Next
    INDEX
    Explanations

    references to stealth capabilities

    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
     LLP
    -0.66
    vance
    -0.59
    ApiModel
    -0.58
    brochen
    -0.52
     kasarigan
    -0.51
    ására
    -0.50
    hearts
    -0.50
    ynth
    -0.50
    })`
    -0.50
    WebServlet
    -0.49
    POSITIVE LOGITS
     Liber
    1.09
    Liber
    0.89
    liber
    0.79
    clad
    0.77
    colo
    0.76
     quarks
    0.74
     препратки
    0.72
     liber
    0.71
     Stealth
    0.70
     Roskov
    0.69
    Activations Density 0.003%

    No Known Activations