© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26165
    Prev
    Next
    INDEX
    Explanations

    references to scientific tables or figures

    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
    verwijspagina
    -0.90
    bitat
    -0.71
     Vann
    -0.71
    OGND
    -0.65
     Rhea
    -0.64
    Hochspringen
    -0.62
    解
    -0.62
     ke
    -0.61
    book
    -0.60
    (!__
    -0.60
    POSITIVE LOGITS
    *]
    0.96
    ]").
    0.76
    ."],
    0.73
    [*]
    0.71
    --)
    0.69
    ()])
    0.68
    */)
    0.68
    }])
    0.67
    \"]
    0.67
    [])
    0.67
    Activations Density 0.002%

    No Known Activations