© 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. 8499
    Prev
    Next
    INDEX
    Explanations

    references to manuscripts and their components in a research context

    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
    帖最后由
    -0.85
    Rüyada
    -0.84
    исленность
    -0.79
    NameInMap
    -0.73
    lccn
    -0.71
    AsUp
    -0.66
    Sucesor
    -0.65
    IntoConstraints
    -0.64
    Geplaatst
    -0.63
     Signalez
    -0.60
    POSITIVE LOGITS
    ISupport
    0.57
    XmlAccessType
    0.57
    nagem
    0.56
     ujednoznacz
    0.54
     smuggled
    0.54
    tonode
    0.52
     Winaray
    0.52
    UrlResolution
    0.49
     wrecked
    0.47
    struzione
    0.47
    Activations Density 0.009%

    No Known Activations