© 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. 3226
    Prev
    Next
    INDEX
    Explanations

    references to recognized or established knowledge or facts

    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
    understand
    -0.88
     understand
    -0.83
     understanding
    -0.79
     understands
    -0.75
    understanding
    -0.74
    Understand
    -0.73
    know
    -0.72
     know
    -0.71
    KNOW
    -0.70
     realize
    -0.69
    POSITIVE LOGITS
     known
    2.36
    Known
    2.14
     Known
    2.13
    known
    2.08
     KNOWN
    2.02
    KNOWN
    1.58
     conhecido
    1.55
     conocida
    1.51
     connu
    1.48
     conocido
    1.46
    Activations Density 0.110%

    No Known Activations