© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11159
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progression or continuation of actions

    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
    tvguidetime
    -0.89
    jshint
    -0.83
    omenclature
    -0.77
    RegressionTest
    -0.75
    cheron
    -0.73
    LAV
    -0.71
    AutoField
    -0.71
     minOccurs
    -0.71
    ällor
    -0.71
     Jimi
    -0.71
    POSITIVE LOGITS
     jspb
    0.73
     NAG
    0.57
     ţ
    0.55
    нциклопедия
    0.52
     Marcy
    0.51
     Erle
    0.51
    !&
    0.51
     cetera
    0.50
    ⚠
    0.50
     Ong
    0.50
    Activations Density 0.011%

    No Known Activations