© 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. 17677
    Prev
    Next
    INDEX
    Explanations

    references to numerical data

    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
     NSCoder
    -0.87
    </i>
    -0.84
    ه
    -0.84
    Marlene
    -0.77
    iastical
    -0.77
    rouvez
    -0.76
    </b>
    -0.75
    rrrr
    -0.75
     UITableView
    -0.75
     inder
    -0.74
    POSITIVE LOGITS
    tic
    1.09
    ANTIC
    0.99
     Brito
    0.93
    ic
    0.92
    IC
    0.91
    gic
    0.90
    thique
    0.90
    monic
    0.89
    lic
    0.87
     tonic
    0.86
    Activations Density 0.148%

    No Known Activations