© 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. 26750
    Prev
    Next
    INDEX
    Explanations

    connections and relationships in data, particularly in biological and audio-related contexts

    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
    MigrationBuilder
    -0.91
    +#+#
    -0.77
     kasarigan
    -0.75
    SharedDtor
    -0.74
    jspx
    -0.72
    FunctionFlags
    -0.67
    يكب
    -0.67
    DatabaseError
    -0.66
     '{@
    -0.64
    CodeAttribute
    -0.63
    POSITIVE LOGITS
     Unidas
    0.57
     each
    0.52
    setLocation
    0.52
    WebMethod
    0.52
     alimentaire
    0.50
    ต่างๆ
    0.49
     similar
    0.49
    обходи
    0.48
     gestation
    0.48
     nødven
    0.48
    Activations Density 0.122%

    No Known Activations