© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14127
    Prev
    Next
    INDEX
    Explanations

    information related to providing guidance or instructions

    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
     שוליים
    -0.68
     Jesucristo
    -0.65
     tahu
    -0.62
     conosce
    -0.59
     basée
    -0.59
     réglable
    -0.56
     huom
    -0.56
     للمعارف
    -0.56
    AsUp
    -0.56
     juos
    -0.55
    POSITIVE LOGITS
     inform
    2.48
     Inform
    2.33
    inform
    2.25
    Inform
    2.20
     informing
    1.34
     INFORM
    1.21
     informs
    1.10
     informe
    0.95
    InputBorder
    0.95
    Informal
    0.92
    Activations Density 0.003%

    No Known Activations