© 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. 15306
    Prev
    Next
    INDEX
    Explanations

    references to causation or causes

    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
    SuppressLint
    -0.76
     beginnetje
    -0.69
     unknownFields
    -0.68
    WithIOException
    -0.66
    RenderAtEndOf
    -0.65
     causing
    -0.63
    tvguidetime
    -0.61
    ✨:
    -0.60
    Twig
    -0.59
     Monfieur
    -0.59
    POSITIVE LOGITS
    cause
    2.14
    Cause
    1.70
    CAUSE
    1.49
     Cause
    0.98
    bout
    0.79
     CAUSE
    0.74
    here
    0.67
    thenReturn
    0.64
    till
    0.63
    Cuz
    0.63
    Activations Density 0.001%

    No Known Activations