© 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. 3064
    Prev
    Next
    INDEX
    Explanations

    details about an invention and its specific applications

    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
    AddHtmlAttribute
    -0.84
    AddTagHelper
    -0.71
    Datuak
    -0.69
     propOrder
    -0.66
    TabLayout
    -0.63
     unknownFields
    -0.63
    adaptiveStyles
    -0.63
     Vikipedi
    -0.61
     محفوظة
    -0.61
    archiviato
    -0.61
    POSITIVE LOGITS
     particular
    0.49
    BorderFactory
    0.46
    particular
    0.45
     specific
    0.44
    voorbeeld
    0.44
     konkrét
    0.44
    fällig
    0.43
    ArrowToggle
    0.42
    ttemberg
    0.42
    Particular
    0.42
    Activations Density 0.730%

    No Known Activations