© 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. 12332
    Prev
    Next
    INDEX
    Explanations

    product descriptions related to image representation and size specifications

    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
    ngdoc
    -0.75
    SourceChecksum
    -0.73
     itſelf
    -0.63
     Oggi
    -0.63
    MemoryWarning
    -0.62
     defStyleAttr
    -0.62
    
    -0.62
    ViewInit
    -0.60
    AxisAlignment
    -0.59
     DÍA
    -0.59
    POSITIVE LOGITS
    tvguidetime
    0.51
    பா
    0.50
    hdl
    0.48
    /*---
    0.48
    abili
    0.47
    //-->
    0.47
     mills
    0.47
     Etsy
    0.47
    Due
    0.47
    ]_
    0.46
    Activations Density 0.046%

    No Known Activations