© 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. 10213
    Prev
    Next
    INDEX
    Explanations

    technical terms related to definitions or specifications in a formal context

    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
     AssemblyTitle
    -0.71
     ſtre
    -0.68
     ſch
    -0.64
    الإنجليزية
    -0.62
     وتسجيلات
    -0.61
    raisemb
    -0.61
     chol
    -0.59
    LoadScene
    -0.59
     enfans
    -0.59
     aDecoder
    -0.59
    POSITIVE LOGITS
    ostock
    0.65
     Janeiro
    0.56
    aturen
    0.51
    })]
    0.51
    ]})
    0.51
    naeus
    0.50
    
    0.50
    ignty
    0.50
    PrivateRoute
    0.49
     beginnetje
    0.48
    Activations Density 0.000%

    No Known Activations