© 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. 3907
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions, limitations, or inclusions in a legal or technical 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
     avoient
    -0.68
     enfans
    -0.66
     disambiguazione
    -0.66
     auroit
    -0.65
     invokingState
    -0.65
     osserva
    -0.63
    RegistryLite
    -0.62
    îtra
    -0.62
     fleste
    -0.61
    AsUp
    -0.61
    POSITIVE LOGITS
     toro
    0.60
     BoxDecoration
    0.58
     AssemblyCulture
    0.58
    putan
    0.58
    はもちろん
    0.54
    googleapis
    0.51
    ypress
    0.51
    hove
    0.51
     בלב
    0.51
     saites
    0.50
    Activations Density 0.291%

    No Known Activations