© 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. 21169
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential problems or issues

    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
     saites
    -0.75
     يتيمه
    -0.71
     MERCHANTABILITY
    -0.68
    IVEREF
    -0.68
    fromnode
    -0.65
     surla
    -0.63
    🔕
    -0.60
    TEMPO
    -0.57
     laude
    -0.56
     comuniques
    -0.56
    POSITIVE LOGITS
    PageFactory
    0.63
     Wikimedijinoj
    0.59
    reich
    0.59
    autant
    0.53
    ַי
    0.53
    ষ্
    0.52
    lidene
    0.51
    鰭
    0.49
    xtext
    0.49
    arev
    0.49
    Activations Density 0.038%

    No Known Activations