© 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. 20115
    Prev
    Next
    INDEX
    Explanations

    sequences of whitespace or blank spaces

    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
    MENAFN
    -0.73
     referrerpolicy
    -0.60
    ]]=
    -0.59
    └──
    -0.58
    steamcommunity
    -0.58
    Mek
    -0.57
    }}/>
    -0.57
    wieś
    -0.56
    ()")
    -0.56
    <>());
    -0.56
    POSITIVE LOGITS
     AssemblyCulture
    0.74
     InputDecoration
    0.73
    WithIOException
    0.67
     Réponses
    0.66
    LEncoder
    0.60
    ArgsConstructor
    0.59
    tagHelperRunner
    0.59
     quorum
    0.58
    issauga
    0.57
    DoubleQuotes
    0.57
    Activations Density 0.024%

    No Known Activations