© 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. 180
    Prev
    Next
    INDEX
    Explanations

    words relating to a criminal investigation, especially descriptions of violence and pursuit.

    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
    Tembelea
    -0.67
    racite
    -0.59
    تاح
    -0.54
    hips
    -0.53
     equator
    -0.52
    jmniej
    -0.52
    ArgsConstructor
    -0.52
    vellous
    -0.52
    โปร
    -0.50
    fjspx
    -0.50
    POSITIVE LOGITS
     injuries
    0.90
     police
    0.89
     injuring
    0.88
     handcu
    0.83
     intoxicated
    0.82
     injured
    0.82
     assailants
    0.82
     paramedics
    0.81
     unconscious
    0.80
     gunshot
    0.79
    Activations Density 3.352%

    No Known Activations