© 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. 28331
    Prev
    Next
    INDEX
    Explanations

    sections that declare competing interests or conflicts of interest

    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
    Vorlage
    -0.59
     Ar
    -0.56
     Ca
    -0.55
    </td>
    -0.54
    WriteLiteral
    -0.54
     Po
    -0.54
     القدم
    -0.53
     protoimpl
    -0.52
     or
    -0.52
    Ar
    -0.52
    POSITIVE LOGITS
     Monfieur
    1.17
     quæ
    1.02
     Majefty
    1.02
     purpoſe
    1.00
    :**
    0.98
     leaſt
    0.97
     fubject
    0.96
     himſelf
    0.94
     leſs
    0.93
     ſeveral
    0.93
    Activations Density 0.004%

    No Known Activations