© 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. 25683
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and formal titles or classifications

    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
    पया
    -0.50
    Aiheesta
    -0.50
     الحره
    -0.48
     JpaRepository
    -0.48
    씩
    -0.46
    Sedangkan
    -0.45
     Liberties
    -0.45
    rrggbb
    -0.44
    Palmarès
    -0.43
     ویژه
    -0.42
    POSITIVE LOGITS
    BeginContext
    0.70
    Gemeinden
    0.60
    /**
    0.59
    )$/,
    0.58
     Insee
    0.57
    󠁮
    0.57
    XmlAccessType
    0.56
    AndEndTag
    0.56
    findpost
    0.56
    "}>
    0.55
    Activations Density 0.468%

    No Known Activations