© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11952
    Prev
    Next
    INDEX
    Explanations

    terms related to sexual harassment and discrimination claims

    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
    issner
    -0.52
    pensive
    -0.48
     banca
    -0.48
    IsPostBack
    -0.45
     cilind
    -0.43
    "%(
    -0.43
    eably
    -0.42
    ξύ
    -0.42
     thập
    -0.41
     parallelogram
    -0.41
    POSITIVE LOGITS
    complexContent
    0.79
     autorytatywna
    0.74
     يتيمه
    0.71
    Portail
    0.68
     незавершена
    0.67
    setupUi
    0.65
    AnimationsModule
    0.64
    InjectAttribute
    0.63
    Personendaten
    0.63
     Infórmanos
    0.63
    Activations Density 0.199%

    No Known Activations