© 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. 6398
    Prev
    Next
    INDEX
    Explanations

    references to objects or items designed to provide comfort or fit

    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
     صوتيه
    -0.71
    lossians
    -0.68
    posia
    -0.65
    bootstrapcdn
    -0.63
    liflower
    -0.63
    ########.
    -0.62
     Keyes
    -0.61
     חיצוניים
    -0.60
    CRIM
    -0.60
    VIAF
    -0.59
    POSITIVE LOGITS
     comfortable
    3.25
     Comfortable
    2.92
     comfort
    2.91
    comfortable
    2.91
    Comfortable
    2.77
     COMFORT
    2.75
    Comfort
    2.72
    comfort
    2.69
     Comfort
    2.67
     comfy
    2.59
    Activations Density 0.007%

    No Known Activations