© 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. 22-RES-MATRYOSHKA-DC
    7. 2315
    Prev
    Next
    INDEX
    Explanations

    the word "and" especially when near a determiner

    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.22.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.22.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
     yet
    -0.59
     löytyy
    -0.59
     while
    -0.57
     voren
    -0.57
     when
    -0.55
     will
    -0.54
     can
    -0.54
     if
    -0.53
     since
    -0.52
     has
    -0.52
    POSITIVE LOGITS
     other
    1.20
    other
    1.03
     autres
    1.01
     outros
    0.92
     demás
    0.88
     otros
    0.88
     outras
    0.87
     its
    0.85
     anderer
    0.85
     Other
    0.84
    Activations Density 0.775%

    No Known Activations