© 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. 9686
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups of people, often highlighting the absence or presence of individuals

    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
     kind
    -0.84
     '@/
    -0.74
     people
    -0.73
     kinds
    -0.66
    SocketAddress
    -0.66
     Hu
    -0.65
     Mot
    -0.64
    PLING
    -0.63
     Voss
    -0.63
     Tr
    -0.61
    POSITIVE LOGITS
     itſelf
    0.97
     Monfieur
    0.87
     purpoſe
    0.85
     Devonian
    0.81
    ſelves
    0.80
    MLLoader
    0.79
     extingu
    0.78
    ſelf
    0.77
     Anſ
    0.77
     Houſe
    0.77
    Activations Density 0.030%

    No Known Activations