© 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. 18484
    Prev
    Next
    INDEX
    Explanations

    the word "the" at various activation strengths throughout the text

    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
     habet
    -0.63
     noDo
    -0.59
    ایق
    -0.58
    postId
    -0.56
    ρων
    -0.55
     MonoBehaviour
    -0.54
    RefNanny
    -0.54
    @[
    -0.53
    ❋
    -0.53
    Spoljašnje
    -0.52
    POSITIVE LOGITS
     समीक्षक
    0.87
    enumi
    0.81
    tothe
    0.76
    OfThe
    0.71
     ofthe
    0.69
     actionMode
    0.67
    HostException
    0.65
     שוליים
    0.63
     AttributeSet
    0.60
    rethe
    0.60
    Activations Density 0.034%

    No Known Activations