© 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. 24-RES-MATRYOSHKA-DC
    7. 75
    Prev
    Next
    INDEX
    Explanations

    conjunctions and words such as "to", "thus", etc

    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.24.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.24.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
     totiž
    -0.66
     ingenieros
    -0.65
     namelijk
    -0.63
     nemlig
    -0.62
    rspec
    -0.60
    :”
    -0.60
     naselje
    -0.55
    :"
    -0.54
    ">—
    -0.54
    :“
    -0.53
    POSITIVE LOGITS
     hence
    1.76
     therefore
    1.55
     thus
    1.53
     consequently
    1.52
     thereby
    1.46
     then
    1.35
     its
    1.34
    hence
    1.31
     also
    1.27
     whatnot
    1.26
    Activations Density 4.081%

    No Known Activations