© 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. 18-RES-MATRYOSHKA-DC
    7. 557
    Prev
    Next
    INDEX
    Explanations

    the word "those" without regard to context.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    TypedDataSet
    -0.65
    Portale
    -0.62
     JpaRepository
    -0.60
     Superhost
    -0.59
    hoeddwyd
    -0.55
     leksikon
    -0.54
    WebServlet
    -0.54
    ."],
    -0.53
     jeżeli
    -0.53
    the
    -0.53
    POSITIVE LOGITS
     же
    0.74
    enumi
    0.64
     who
    0.64
    portion
    0.64
     pesky
    0.63
    jenigen
    0.62
    genen
    0.62
    tagHelper
    0.61
     виправивши
    0.59
    #%%
    0.58
    Activations Density 0.121%

    No Known Activations