© 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. 2378
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to filling or completing forms and tasks

    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
    rawDesc
    -0.89
    Personendaten
    -0.80
    存于互联网档案馆
    -0.79
     שוליים
    -0.75
    LookAnd
    -0.75
    Obrigada
    -0.74
     podéis
    -0.72
    }{*}{
    -0.71
    BufferException
    -0.70
    chtest
    -0.70
    POSITIVE LOGITS
     fill
    1.63
     FILL
    1.60
    filled
    1.56
     Fill
    1.56
    filling
    1.55
    FILL
    1.52
     filling
    1.51
     Filling
    1.51
     filled
    1.50
    Fill
    1.46
    Activations Density 0.046%

    No Known Activations