© 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. 24374
    Prev
    Next
    INDEX
    Explanations

    structures that involve numeric data and coding errors

    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
     estekak
    -1.02
    存于互联网档案馆
    -1.02
    ंदीखरीदारी
    -1.01
    SceneManagement
    -0.99
     BoxDecoration
    -0.92
     ***!
    -0.90
    GraphicsUnit
    -0.90
    ^(@)
    -0.90
    BeginContext
    -0.89
    ImageContext
    -0.85
    POSITIVE LOGITS
    　
    0.77
    …
    0.69
    a
    0.63
    ”
    0.63
    ...
    0.61
    mota
    0.59
    ta
    0.59
    ?
    0.59
    HA
    0.57
    es
    0.57
    Activations Density 0.190%

    No Known Activations