© 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. 22482
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or numerical values associated with genetic research

    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
    المناصب
    -0.67
     дописавши
    -0.64
    stateProvider
    -0.64
    mybatisplus
    -0.63
    +#+#
    -0.62
    MetaObject
    -0.61
    picasso
    -0.61
     OCS
    -0.60
    reactstrap
    -0.59
     }}"></
    -0.58
    POSITIVE LOGITS
    AFFIRMED
    0.56
    futbolista
    0.55
    writeField
    0.52
     tabindex
    0.50
    cheria
    0.50
    ocere
    0.49
    cokinetics
    0.49
    orrhage
    0.49
    pulumi
    0.48
    erschutz
    0.48
    Activations Density 0.023%

    No Known Activations