© 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. 21073
    Prev
    Next
    INDEX
    Explanations

    patterns and structures related to programming syntax, particularly in object-oriented programming languages

    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
     transfieras
    -0.66
    ikistan
    -0.56
    routeProvider
    -0.52
    glEnd
    -0.50
    IonicModule
    -0.50
    scriptcase
    -0.48
     <<<<<<<<<<<<<<
    -0.48
     isComment
    -0.48
     Reſ
    -0.48
    '])->
    -0.47
    POSITIVE LOGITS
    yntaxException
    0.69
    }")]
    0.65
    URLException
    0.63
    })*/
    0.60
     initComponents
    0.58
     supérieures
    0.58
    __':
    0.57
    abstractmethod
    0.56
    servable
    0.55
    bkz
    0.54
    Activations Density 0.012%

    No Known Activations