© 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. 2690
    Prev
    Next
    INDEX
    Explanations

    words with "ill", "ar", "er", "tr", "ul", "un", "di", "ig", "ac", "re", "op", "ap", or "nucle" letter combinations.

    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
    riwal
    -0.74
     pleaſure
    -0.73
     podjela
    -0.73
     financeira
    -0.72
     Exacts
    -0.71
     bershka
    -0.68
     raiſ
    -0.68
    AttributeSet
    -0.67
    IntoConstraints
    -0.67
     سكانية
    -0.66
    POSITIVE LOGITS
    ums
    0.77
    ous
    0.75
    us
    0.63
    UM
    0.63
    uses
    0.59
    ouss
    0.56
    US
    0.56
    um
    0.56
    umb
    0.55
    ום
    0.54
    Activations Density 0.381%

    No Known Activations