© 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. 4077
    Prev
    Next
    INDEX
    Explanations

    patterns involving the adjacency or proximity between components

    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
     ujednoznacz
    -0.73
    Према
    -0.73
    /></
    -0.71
    tvguidetime
    -0.69
    GEBURTSDATUM
    -0.67
    clusive
    -0.61
     الرياضيه
    -0.60
    mobileqq
    -0.60
    ']],
    -0.59
     Normdatei
    -0.59
    POSITIVE LOGITS
     adjacent
    2.72
     adjoining
    2.36
     Adjacent
    2.36
    adjacent
    2.33
     surrounding
    2.31
     neighboring
    2.30
     neighbouring
    2.30
     nearby
    2.22
    Adjacent
    2.05
    nearby
    1.88
    Activations Density 0.070%

    No Known Activations