© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4376
    Prev
    Next
    INDEX
    Explanations

    references to the label 'relatedness' or mentions of similarity and connection between entities

    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
    hieu
    -0.56
    HAS
    -0.55
     precision
    -0.52
    γω
    -0.51
    Portale
    -0.50
     accuracy
    -0.49
    imax
    -0.48
     integrity
    -0.48
     apl
    -0.48
     tot
    -0.47
    POSITIVE LOGITS
    ness
    3.88
    NESS
    3.08
    nesses
    2.44
     ness
    1.79
    iness
    1.63
    eness
    1.51
    neſs
    1.50
    nesse
    1.48
    nefs
    1.40
    Ness
    1.38
    Activations Density 0.030%

    No Known Activations