© 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. 14136
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate reluctance or negative outcomes in various contexts

    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
     paljon
    -0.50
    principalTable
    -0.48
     much
    -0.47
    もう少し
    -0.47
    很好的
    -0.46
    usaha
    -0.46
     stava
    -0.46
    Same
    -0.45
     frecuentes
    -0.45
     túnel
    -0.45
    POSITIVE LOGITS
     تضيفلها
    0.82
     Signalez
    0.75
    ValueStyle
    0.75
    tagHelperRunner
    0.71
    Lá
    0.68
     وتسجيلات
    0.68
     jamais
    0.67
    ngOnInit
    0.67
    ništ
    0.67
    aarrggbb
    0.66
    Activations Density 0.048%

    No Known Activations