© 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. 28265
    Prev
    Next
    INDEX
    Explanations

    instances of encouragement or supportive language

    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
     بيها
    -0.84
    id
    -0.68
    Bae
    -0.66
     Bae
    -0.66
    en
    -0.66
    println
    -0.64
    machte
    -0.64
    quad
    -0.63
     Koz
    -0.62
     Фа
    -0.62
    POSITIVE LOGITS
    couragement
    1.15
    couraged
    1.14
     discouraged
    1.05
    encouragement
    1.02
    couraging
    0.98
     discourage
    0.95
     encouragement
    0.94
    multer
    0.93
     encouraged
    0.91
     Encourage
    0.88
    Activations Density 0.008%

    No Known Activations