© 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. 28688
    Prev
    Next
    INDEX
    Explanations

    phrases related to discrimination and retaliation in employment

    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
    Sabato
    -0.49
    ppins
    -0.48
     cref
    -0.48
    lini
    -0.46
    SizeF
    -0.44
    ValueStyle
    -0.44
    ?):
    -0.43
     simplifié
    -0.43
    ])+
    -0.42
     sabato
    -0.42
    POSITIVE LOGITS
     MainAxisSize
    0.68
    glBindTexture
    0.63
    SourceChecksum
    0.63
     onPostExecute
    0.62
    Jereo
    0.62
     interview
    0.58
    ervé
    0.56
    іга
    0.56
    skype
    0.56
    ьа
    0.55
    Activations Density 0.042%

    No Known Activations