© 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. 3836
    Prev
    Next
    INDEX
    Explanations

    instances of the word "respect" and related phrases

    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
    OGND
    -0.86
    Chham
    -0.75
     Aene
    -0.74
     tabPage
    -0.72
     dandy
    -0.71
     triangulation
    -0.70
    medies
    -0.69
    ✨:
    -0.69
    bleau
    -0.69
     GOV
    -0.67
    POSITIVE LOGITS
     respect
    1.49
     Respect
    1.49
    Respect
    1.41
     RESPECT
    1.34
    respect
    1.29
     respects
    1.12
     respek
    1.10
     respecting
    1.05
    respected
    1.03
     respecte
    1.03
    Activations Density 0.076%

    No Known Activations