© 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. 0-RES-MATRYOSHKA-DC
    7. 12466
    Prev
    Next
    INDEX
    Explanations

    references to the concept of a successor in a sequence or hierarchy

    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
    pernicus
    -0.48
     boy
    -0.47
    cinia
    -0.47
     together
    -0.46
     rest
    -0.45
     conci
    -0.45
     Quảng
    -0.45
     점
    -0.45
     lod
    -0.45
     מוכ
    -0.43
    POSITIVE LOGITS
     successor
    3.03
     successors
    2.41
    successor
    2.23
     predecessor
    1.78
     Nachfolger
    1.63
     predecessors
    1.30
    prede
    1.13
    Prede
    1.10
     predecess
    1.02
     prédé
    0.84
    Activations Density 0.002%

    No Known Activations