© 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. 17860
    Prev
    Next
    INDEX
    Explanations

    phrases relating to probabilities and combinations involving letters

    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
     AppComponent
    -0.44
     ap
    -0.44
     vs
    -0.40
     Terr
    -0.38
     versus
    -0.38
     Internet
    -0.38
    jec
    -0.36
    скай
    -0.36
    fitting
    -0.36
     المحت
    -0.36
    POSITIVE LOGITS
     كومونز
    1.02
    ValueStyle
    0.98
    tagHelperRunner
    0.92
    ✨:
    0.90
     հղումներ
    0.87
    новниш
    0.86
    :✨
    0.86
     ligiloj
    0.86
     <>",
    0.83
    RegressionTest
    0.82
    Activations Density 0.008%

    No Known Activations