© 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. 22756
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss the complexity and challenges of verifying facts or issues

    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
     kaynağından
    -0.50
     ]}
    -0.50
    hasMoreElements
    -0.48
     somewhere
    -0.46
    ::::::::
    -0.46
    一个个
    -0.46
    dailymail
    -0.46
    ρεύ
    -0.46
    ̣ng
    -0.45
     Reggie
    -0.44
    POSITIVE LOGITS
    ViewFeatures
    0.69
    AnimationsModule
    0.69
    AddTagHelper
    0.64
    InputTagHelper
    0.60
    tvguidetime
    0.60
    saraba
    0.58
    hibli
    0.58
    BASEPATH
    0.58
    intios
    0.57
    تقاوى
    0.57
    Activations Density 0.113%

    No Known Activations