© 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. 26553
    Prev
    Next
    INDEX
    Explanations

    references to varying degrees of mildness in conditions or symptoms

    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
    ="@+
    -0.75
    </thead>
    -0.73
    पया
    -0.72
     Hara
    -0.72
     Olsson
    -0.70
     Schuster
    -0.69
    Ạ
    -0.69
    ográ
    -0.68
    lawayo
    -0.67
     "..\..\
    -0.66
    POSITIVE LOGITS
    Mild
    0.98
     Mildred
    0.94
    mild
    0.91
     Mild
    0.89
     mild
    0.79
     mildly
    0.74
     Pliocene
    0.74
     gild
    0.73
     Jefus
    0.72
     ſte
    0.70
    Activations Density 0.002%

    No Known Activations