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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19731
    Prev
    Next
    INDEX
    Explanations

    terms related to sexual harassment

    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
     AspNetCore
    -0.91
    abestanden
    -0.91
     BorderSide
    -0.91
     sumpay
    -0.88
     SEDS
    -0.88
     оригіналу
    -0.87
     héro
    -0.87
    IUrlHelper
    -0.87
     ſche
    -0.86
     Reſ
    -0.85
    POSITIVE LOGITS
     Har
    1.28
    Har
    1.27
     HAR
    1.16
    har
    1.13
     har
    1.11
     Harman
    1.09
     Harlow
    1.02
    HAR
    0.99
     Harrell
    0.96
     Harrington
    0.94
    Activations Density 0.024%

    No Known Activations