© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6220
    Prev
    Next
    INDEX
    Explanations

    terms related to various biological and medical conditions or protocols

    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
    Negative Logits
     HasFactory
    -1.02
     متعلقه
    -0.96
    AutoScaleMode
    -0.94
     Magnetism
    -0.91
     Sando
    -0.91
     charset
    -0.88
     Audiodateien
    -0.84
     Anemia
    -0.83
     Zit
    -0.82
     Fet
    -0.81
    POSITIVE LOGITS
     PRO
    1.34
    Pro
    1.31
     Pro
    1.26
    PRO
    1.22
    pro
    1.06
     Prodi
    0.93
    プロ
    0.90
     프로
    0.89
     Prow
    0.88
     Pros
    0.85
    Activations Density 0.308%

    No Known Activations