© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16265
    Prev
    Next
    INDEX
    Explanations

    terms related to turbidity or moral turpitude, typically in legal contexts

    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
     Klon
    -0.91
     EIS
    -0.89
     Sienna
    -0.88
     AIAA
    -0.87
     Brennan
    -0.84
     pstmt
    -0.83
     Sien
    -0.83
     doigts
    -0.81
     Amiens
    -0.80
     Bauhaus
    -0.79
    POSITIVE LOGITS
     Tur
    1.68
    Tur
    1.55
     TUR
    1.47
    tur
    1.41
    TUR
    1.38
     tur
    1.35
     Turf
    0.97
     turkeys
    0.97
     turkey
    0.95
     Turbo
    0.92
    Activations Density 0.012%

    No Known Activations