© 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. 15295
    Prev
    Next
    INDEX
    Explanations

    references to medical or pharmaceutical substances, particularly medications

    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
    kool
    -0.63
    IsMutable
    -0.61
    COUVER
    -0.60
    outState
    -0.57
     übersch
    -0.53
     fleste
    -0.52
     ose
    -0.51
    ungkinan
    -0.51
     kjem
    -0.50
     numberOfRows
    -0.50
    POSITIVE LOGITS
     navbar
    0.89
    gwt
    0.87
    Datuak
    0.83
     lick
    0.68
     fil
    0.68
     endometri
    0.67
    profen
    0.65
     Jos
    0.65
    avir
    0.65
     courtroom
    0.63
    Activations Density 0.108%

    No Known Activations