© 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. 23365
    Prev
    Next
    INDEX
    Explanations

    phrases indicating successful outcomes or functionality

    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
    aarrggbb
    -0.65
     تضيفلها
    -0.47
    HasAnnotation
    -0.47
    gameserver
    -0.46
     nemmeno
    -0.46
     Appellate
    -0.45
    BrowserRouter
    -0.44
     vs
    -0.43
     gobernador
    -0.43
     porcelana
    -0.41
    POSITIVE LOGITS
    TargetException
    0.66
     purpoſe
    0.65
    aliere
    0.63
     houſe
    0.63
     himſelf
    0.61
    icksburg
    0.60
     myſelf
    0.60
     pleaſure
    0.59
     fubject
    0.59
    iestety
    0.57
    Activations Density 0.021%

    No Known Activations