© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 64
    Prev
    Next
    INDEX
    Explanations

    words relating to programming, websites or software, including styles (CSS), companies and software methods, as well as database tables with user centric information.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    MigrationBuilder
    -0.93
     Normdatei
    -0.88
     internetowa
    -0.86
    GraphicsUnit
    -0.82
    sidemargin
    -0.80
     مشين
    -0.76
    EDEFAULT
    -0.75
    endphp
    -0.75
    swire
    -0.74
    Chham
    -0.73
    POSITIVE LOGITS
     themselves
    0.98
     are
    0.93
    hips
    0.89
     were
    0.71
    יהם
    0.70
     galore
    0.68
     neler
    0.68
     jotka
    0.67
    capes
    0.65
    themselves
    0.62
    Activations Density 6.189%

    No Known Activations