© 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. 12-RES-MATRYOSHKA-DC
    7. 4595
    Prev
    Next
    INDEX
    Explanations

    dialogue or quotations in the text

    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
    Geplaatst
    -0.70
    MENAFN
    -0.69
    Datuak
    -0.69
    ſelf
    -0.68
     ſche
    -0.67
     doubtnut
    -0.66
     deſt
    -0.63
    Gambas
    -0.63
     purpoſe
    -0.62
     itſelf
    -0.62
    POSITIVE LOGITS
    іга
    0.56
     baru
    0.44
    itively
    0.44
    vider
    0.43
     noDo
    0.43
     <=",
    0.43
    legten
    0.43
    TokenNameRBRACE
    0.43
    baru
    0.42
     yeter
    0.42
    Activations Density 0.034%

    No Known Activations