© 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. 12-RES-MATRYOSHKA-DC
    7. 16675
    Prev
    Next
    INDEX
    Explanations

    keywords related to medical procedures and their results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.64
     estimés
    -0.63
     itſelf
    -0.62
     Monfieur
    -0.61
     himſelf
    -0.61
     ſta
    -0.60
    MLLoader
    -0.60
     myſelf
    -0.59
     uſ
    -0.57
     purpoſe
    -0.57
    POSITIVE LOGITS
     sauf
    0.68
    except
    0.65
     except
    0.63
     excepto
    0.59
    []):
    0.58
    Including
    0.58
    Except
    0.56
     Including
    0.56
    même
    0.55
     Except
    0.51
    Activations Density 0.215%

    No Known Activations