© 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. 22-RES-MATRYOSHKA-DC
    7. 2536
    Prev
    Next
    INDEX
    Explanations

    passages about systematic and legal processes but also finding more basic articles like "the", "a", or "in" within those passages

    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
    rungsseite
    -0.66
    ipfel
    -0.63
    SuppressLint
    -0.59
     שוליים
    -0.58
    الحياه
    -0.56
    érêt
    -0.56
    iello
    -0.53
    engagent
    -0.53
    MemoryWarning
    -0.52
     المحت
    -0.52
    POSITIVE LOGITS
     system
    1.40
     structure
    1.37
     systems
    1.20
     sistema
    1.16
     structures
    1.14
    ssystem
    1.14
    system
    1.13
     système
    1.13
     Structure
    1.12
     SYSTEM
    1.12
    Activations Density 0.779%

    No Known Activations