© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1291
    Prev
    Next
    INDEX
    Explanations

    descriptions of structures composed of multiple assembled parts

    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
    IntoConstraints
    -0.66
    ukone
    -0.63
     forthcoming
    -0.63
    bių
    -0.58
     discerning
    -0.57
    Threading
    -0.56
    horst
    -0.56
     propensity
    -0.56
    ഈ
    -0.56
    xfc
    -0.55
    POSITIVE LOGITS
     consists
    2.72
     consist
    2.50
     consisted
    2.34
     consiste
    2.16
     consisting
    2.08
     comprises
    1.88
     består
    1.84
     terdiri
    1.76
     comprise
    1.72
     belong
    1.51
    Activations Density 0.621%

    No Known Activations