© 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. 8540
    Prev
    Next
    INDEX
    Explanations

    references to educational backgrounds and academic affiliations

    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
     nakalista
    -0.74
    ItemBackground
    -0.72
    ]='\
    -0.72
    atshirt
    -0.64
    PullParser
    -0.64
    Newspaper
    -0.62
     elastici
    -0.62
    rawDesc
    -0.61
    offsetof
    -0.60
     ExecuteAsync
    -0.60
    POSITIVE LOGITS
     voorzien
    0.50
    تفصیلات
    0.50
     África
    0.49
    cassert
    0.47
    ässer
    0.45
     jäsen
    0.45
     arasında
    0.44
    idence
    0.43
    Resizable
    0.42
    Begriffsklä
    0.42
    Activations Density 0.009%

    No Known Activations