© 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. 30723
    Prev
    Next
    INDEX
    Explanations

    negative indicators or terms related to significant outcomes or metrics

    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
     propOrder
    -1.02
    IsMutable
    -1.01
     betweenstory
    -0.97
     Normdatei
    -0.86
    URLException
    -0.79
     समीक्षक
    -0.78
    PerformLayout
    -0.74
     صوتيه
    -0.73
     فريبيس
    -0.72
     HttpNotFound
    -0.71
    POSITIVE LOGITS
     åt
    0.49
     Original
    0.46
     Ing
    0.46
     Sas
    0.46
     popolo
    0.45
     Ersten
    0.45
    備
    0.45
     Sa
    0.44
     Shand
    0.44
     näm
    0.44
    Activations Density 0.290%

    No Known Activations