© 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. 14877
    Prev
    Next
    INDEX
    Explanations

    language related to expressions of hate or derogatory comments directed at individuals or groups

    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
    AppCompat
    -0.57
     stories
    -0.52
    文章
    -0.51
     document
    -0.51
     note
    -0.50
     detal
    -0.50
     detail
    -0.50
    FileDescriptor
    -0.50
     chronicles
    -0.49
    وض
    -0.47
    POSITIVE LOGITS
     uttered
    0.92
     uttering
    0.75
     utterances
    0.71
    glGen
    0.70
    makeConstraints
    0.69
    ConstraintMaker
    0.68
     utterance
    0.67
    DispatchToProps
    0.66
    فاده
    0.66
     GenerationType
    0.66
    Activations Density 0.098%

    No Known Activations