© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 261
    Prev
    Next
    INDEX
    Explanations

    language related to criminal activity and legal proceedings

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    complexContent
    -0.91
    Datuak
    -0.88
    出版年
    -0.68
     linkovi
    -0.65
    ClientSize
    -0.60
    GraphicsUnit
    -0.59
    Hozzáférés
    -0.57
    tonode
    -0.56
    })));
    -0.56
     Процитовано
    -0.56
    POSITIVE LOGITS
     fraud
    1.13
     fraudulent
    1.07
     illegal
    1.06
     illicit
    1.02
     crimes
    1.02
     stealing
    1.01
     cheating
    1.01
     theft
    1.01
     dishonest
    0.95
    fraud
    0.92
    Activations Density 4.466%

    No Known Activations