© 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. 19924
    Prev
    Next
    INDEX
    Explanations

    specific formats and patterns typically associated with structured data, possibly code or mathematical expressions

    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
     تضيفلها
    -0.96
    ++
    -0.72
     IBOutlet
    -0.70
    <>();
    -0.70
    forKey
    -0.67
    )}</
    -0.67
    migrationBuilder
    -0.65
     createState
    -0.65
    JScrollPane
    -0.65
    writeField
    -0.65
    POSITIVE LOGITS
     endlich
    0.47
     animale
    0.47
     pourriez
    0.46
     ganglia
    0.45
    fromnode
    0.44
     baratos
    0.44
     stupidly
    0.43
    vy
    0.42
     certes
    0.42
     gratuites
    0.42
    Activations Density 0.063%

    No Known Activations