© 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. 6230
    Prev
    Next
    INDEX
    Explanations

    mentions of being accompanied or supported, often with a high activation when this concept appears

    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
     OnInit
    -0.63
     acres
    -0.59
    atorship
    -0.58
    osoba
    -0.58
     chantier
    -0.55
    ölkerung
    -0.54
    Firing
    -0.54
     bled
    -0.54
    tidase
    -0.54
     nada
    -0.53
    POSITIVE LOGITS
     accompany
    3.16
     accompanies
    3.06
     accompanied
    3.00
     accompanying
    2.88
    accompanied
    2.55
     accompagn
    2.52
    companied
    2.36
    companying
    2.36
     acompañ
    2.28
     accompaniment
    2.27
    Activations Density 0.054%

    No Known Activations