© 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. 22711
    Prev
    Next
    INDEX
    Explanations

    details related to educational or professional credentials in the context of media or technology

    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
     ModelExpression
    -0.84
     समीक्षक
    -0.83
    +#+
    -0.77
    ConstraintMaker
    -0.73
     AssemblyCulture
    -0.73
     فريبيس
    -0.72
    IUrlHelper
    -0.72
    AddTagHelper
    -0.71
     jsPsych
    -0.70
    </caption>
    -0.70
    POSITIVE LOGITS
    marvin
    0.54
    ديو
    0.50
    SEY
    0.46
    UPO
    0.46
    velocityY
    0.45
     listOf
    0.45
    <bos>
    0.44
     Tit
    0.43
    tient
    0.43
    ngthen
    0.42
    Activations Density 0.053%

    No Known Activations