© 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. 13939
    Prev
    Next
    INDEX
    Explanations

    references to precise actions of stepping or stepping onto, indicating it is looking for mentions of the act of stepping

    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
    Tembelea
    -0.61
    IsMutable
    -0.59
    Erreferentziak
    -0.57
    pement
    -0.54
    Groom
    -0.53
     initComponents
    -0.52
     numberOfRows
    -0.52
    esModule
    -0.50
    jstor
    -0.50
     الحره
    -0.50
    POSITIVE LOGITS
     stepped
    2.58
     stepping
    2.58
     Stepping
    2.25
    Stepping
    2.02
    stepping
    1.94
     Roskov
    0.70
    ')],
    0.63
     stepper
    0.61
     Ste
    0.60
    stepper
    0.60
    Activations Density 0.001%

    No Known Activations