© 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. 224
    Prev
    Next
    INDEX
    Explanations

    references to specific actions involving locating, establishing, or controlling particular information or objects

    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
    ⓧ
    -1.09
     AssemblyProduct
    -0.93
     propOrder
    -0.92
     كومونز
    -0.91
    Lähteet
    -0.89
    cessite
    -0.89
    :✨
    -0.88
     nakalista
    -0.87
    Rujuakan
    -0.86
    bootstrapcdn
    -0.86
    POSITIVE LOGITS
     отношению
    0.54
    The
    0.49
    to
    0.48
    ron
    0.46
    was
    0.46
    Was
    0.46
    To
    0.45
    あった
    0.44
    ‘
    0.43
     Was
    0.43
    Activations Density 4.015%

    No Known Activations