© 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. 6397
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and relationships involving matrices and their properties

    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
     nahilalakip
    -0.90
    MemoryWarning
    -0.88
    fjspx
    -0.87
    tagHelperRunner
    -0.86
     estekak
    -0.77
     nakalista
    -0.73
    enterOuterAlt
    -0.72
    verwijspagina
    -0.70
     crf
    -0.69
     combineReducers
    -0.69
    POSITIVE LOGITS
    <bos>
    0.40
    hoda
    0.40
     mor
    0.39
     gjø
    0.39
     <
    0.39
     Bug
    0.38
    faccia
    0.38
    greenrobot
    0.37
     köl
    0.37
    prender
    0.36
    Activations Density 0.178%

    No Known Activations