© 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. 2735
    Prev
    Next
    INDEX
    Explanations

    references to meta-analyses and related metadata in research documents

    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
    //
    -0.93
    GHIJKLM
    -0.91
    Samson
    -0.88
     DriverManager
    -0.87
     ControllerBase
    -0.81
     Arbor
    -0.76
    vocable
    -0.75
     Samson
    -0.73
    noin
    -0.72
     arbor
    -0.71
    POSITIVE LOGITS
    meta
    1.55
     Meta
    1.48
     meta
    1.45
     META
    1.44
    Meta
    1.37
     méta
    1.18
     MET
    1.15
    META
    1.14
     metaphysics
    1.11
     Metab
    1.06
    Activations Density 0.054%

    No Known Activations