© 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. 11504
    Prev
    Next
    INDEX
    Explanations

    both instances of the word "in" and phrases indicating location

    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
    الحياه
    -0.80
     Anſ
    -0.70
     initComponents
    -0.69
     cuffs
    -0.68
     IFT
    -0.65
     fufficient
    -0.65
    RenderAtEndOf
    -0.65
     throats
    -0.64
     Hopf
    -0.64
    клопе
    -0.63
    POSITIVE LOGITS
    setViewportView
    0.49
    isinin
    0.49
     proposons
    0.47
    NameInMap
    0.46
    jerc
    0.45
    TAWA
    0.45
    |=\
    0.45
    thenReturn
    0.44
    dataflow
    0.44
    revalidate
    0.44
    Activations Density 0.037%

    No Known Activations