© 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. 26934
    Prev
    Next
    INDEX
    Explanations

    phrases indicating limitations or problems in a context

    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
    Negative Logits
     kind
    -0.54
    uxxxx
    -0.53
    eloma
    -0.50
    plain
    -0.49
    Parallel
    -0.48
    findpost
    -0.48
    Clik
    -0.47
     alike
    -0.46
     plain
    -0.46
    спу
    -0.45
    POSITIVE LOGITS
     الرياضيه
    0.72
    oa̍t
    0.70
    awtextra
    0.70
     defaultstate
    0.68
    <?
    0.67
    :+:
    0.65
    antaine
    0.63
     JpaRepository
    0.63
    IsMutable
    0.58
     betweenstory
    0.58
    Activations Density 0.091%

    No Known Activations