© 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. 23754
    Prev
    Next
    INDEX
    Explanations

    references to data packets

    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
    ه
    -0.85
     istore
    -0.79
     Bergh
    -0.77
    ://
    -0.71
    package
    -0.70
    fillStyle
    -0.65
     estimés
    -0.65
     पार
    -0.64
    hofen
    -0.63
    WriteBarrier
    -0.63
    POSITIVE LOGITS
     packets
    1.38
     Packet
    1.32
    Packet
    1.23
    packets
    1.23
     packet
    1.12
    PACKET
    1.07
    packet
    1.06
    Packets
    0.99
    Zet
    0.87
     creeks
    0.85
    Activations Density 0.008%

    No Known Activations