© 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. 12-RES-MATRYOSHKA-DC
    7. 2853
    Prev
    Next
    INDEX
    Explanations

    references to figures or tables in a document

    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
    LookAnd
    -0.84
     AssemblyCulture
    -0.82
    Personendaten
    -0.77
     Roskov
    -0.77
     Италијани
    -0.76
     ویکی‌پدیا
    -0.73
     kasarigan
    -0.71
     AssemblyProduct
    -0.68
     Efq
    -0.67
    Personensuche
    -0.66
    POSITIVE LOGITS
    SeekBar
    0.66
    pez
    0.63
    pede
    0.63
    IsContent
    0.61
     Aer
    0.60
    bcd
    0.59
    sendKeys
    0.58
    rawDesc
    0.58
    zana
    0.57
    mud
    0.57
    Activations Density 0.016%

    No Known Activations