© 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. 23578
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical solvents and their properties

    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
    Zunanje
    -0.53
     estekak
    -0.51
    IBOutlet
    -0.49
    UNDEFINED
    -0.49
    ностью
    -0.45
    RenderAtEndOf
    -0.44
     devices
    -0.43
    UnitOfWork
    -0.43
    <
    -0.42
     device
    -0.42
    POSITIVE LOGITS
    تقاوى
    0.91
    esModule
    0.88
    ंदीखरीदारी
    0.88
    rungsseite
    0.82
    rawDesc
    0.77
     виправивши
    0.71
     StringTokenizer
    0.71
    ])));
    0.70
     pinulongan
    0.69
    =$?
    0.67
    Activations Density 0.298%

    No Known Activations