© 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. 19894
    Prev
    Next
    INDEX
    Explanations

    references to specific compositions or formulations, particularly in a scientific or patent context

    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
    rungsseite
    -1.01
    complexType
    -0.73
     الحره
    -0.68
    ibatis
    -0.65
     composites
    -0.63
    Fuse
    -0.62
     composite
    -0.61
    انيف
    -0.61
     Maia
    -0.57
     fieldNum
    -0.57
    POSITIVE LOGITS
    keiten
    0.77
    PREC
    0.71
    etsk
    0.70
    riedenheit
    0.68
    unen
    0.66
     JpaRepository
    0.65
     Joaquín
    0.65
    SLA
    0.65
    kinson
    0.64
     whit
    0.64
    Activations Density 0.006%

    No Known Activations