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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12317
    Prev
    Next
    INDEX
    Explanations

    boundaries and padding information in layout descriptions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })`
    -0.58
    "]=
    -0.54
    klaim
    -0.51
     linkovi
    -0.49
     displaying
    -0.48
    Quote
    -0.47
    躇
    -0.47
     Claims
    -0.47
    řev
    -0.46
    luß
    -0.46
    POSITIVE LOGITS
    Padding
    3.66
     Padding
    2.03
    DockStyle
    1.06
    PADDING
    0.98
    DrawerToggle
    0.81
    AndroidJUnit
    0.77
    FieldBuilder
    0.76
     lenker
    0.75
     insuffisamment
    0.73
    ArgsConstructor
    0.71
    Activations Density 0.002%

    No Known Activations