© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14002
    Prev
    Next
    INDEX
    Explanations

    passages of text that contain the word "passed" or similar indicators of completion or approval

    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
     passing
    -1.40
     Passing
    -1.19
    Passing
    -1.15
    passing
    -1.09
     passage
    -0.73
     المعيارى
    -0.69
     Passage
    -0.67
     passers
    -0.64
     died
    -0.60
     passer
    -0.60
    POSITIVE LOGITS
     passed
    1.21
    passed
    0.94
     Passed
    0.92
    tagHelperRunner
    0.84
     past
    0.82
    Passed
    0.80
    WebElementEntity
    0.68
     beginnetje
    0.63
    past
    0.62
     beyond
    0.61
    Activations Density 0.006%

    No Known Activations