© 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. 22747
    Prev
    Next
    INDEX
    Explanations

    references to sources and treatments in a document

    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
     inves
    -0.52
    alamat
    -0.46
    TintMode
    -0.45
    avra
    -0.44
     purpoſe
    -0.44
     compter
    -0.43
     uli
    -0.43
     Pág
    -0.43
    انگلیسی
    -0.43
    扼
    -0.43
    POSITIVE LOGITS
    expandindo
    1.09
    Gön
    1.01
    +#+#
    0.90
     Chwiliwch
    0.86
     مرئيه
    0.80
     Audiodateien
    0.75
    tagHelperRunner
    0.70
    OGND
    0.70
    Portail
    0.70
     Wikimedijinoj
    0.68
    Activations Density 0.000%

    No Known Activations