© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11482
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, particularly variable declarations and pointers

    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
    SBATCH
    -0.81
    __':
    -0.80
     createSprite
    -0.79
    sizeCache
    -0.76
     JpaRepository
    -0.75
    AnchorTagHelper
    -0.72
    ]")]
    -0.71
    aarrggbb
    -0.70
    igshid
    -0.69
    dafx
    -0.69
    POSITIVE LOGITS
    ftagPool
    0.41
    uk
    0.40
     opérés
    0.40
    under
    0.39
    вол
    0.37
     StringIO
    0.37
    /
    0.37
     VIAF
    0.36
    Хьажоргаш
    0.36
    тельством
    0.36
    Activations Density 0.247%

    No Known Activations