© 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. 3229
    Prev
    Next
    INDEX
    Explanations

    references to tissue preparation and analysis procedures

    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
     pinulongan
    -0.76
    StructEnd
    -0.73
    XmlEnum
    -0.66
    ?>">
    -0.66
    JNIEnv
    -0.64
    ThroughAttribute
    -0.63
    তথ্যসূত্র
    -0.63
    Numerology
    -0.63
    IContainer
    -0.61
    ReusableCell
    -0.61
    POSITIVE LOGITS
     slice
    0.64
     slices
    0.61
     thin
    0.61
     Slice
    0.60
     slicing
    0.59
     Thin
    0.57
     sliced
    0.56
     thinner
    0.56
    setVerticalGroup
    0.55
     cuts
    0.54
    Activations Density 0.047%

    No Known Activations