© 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. 17578
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate purpose or conjunctions in conditional statements

    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
    Personendaten
    -0.96
    bootstrapcdn
    -0.85
    awtextra
    -0.85
    MemoryWarning
    -0.81
     BorderRadius
    -0.70
     Britton
    -0.68
    addContainerGap
    -0.66
    qian
    -0.65
    ⓧ
    -0.63
    eX
    -0.62
    POSITIVE LOGITS
     να
    0.77
    att
    0.76
    ✤
    0.68
     att
    0.68
     Satt
    0.68
    Pill
    0.67
     Чтобы
    0.67
    NCC
    0.66
     Attribution
    0.64
     Sergi
    0.63
    Activations Density 0.004%

    No Known Activations