© 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. 2021
    Prev
    Next
    INDEX
    Explanations

    words relating to formal processes

    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
     alguno
    -0.52
    ktop
    -0.51
     Somewhere
    -0.50
     concernant
    -0.50
    databind
    -0.49
     basé
    -0.49
     تانيه
    -0.49
     amounting
    -0.49
     tuyo
    -0.48
     riguardo
    -0.48
    POSITIVE LOGITS
     they
    1.38
     we
    1.30
     you
    1.02
     he
    0.99
     used
    0.89
     involved
    0.89
     that
    0.80
     mà
    0.79
     she
    0.79
     jakie
    0.78
    Activations Density 2.815%

    No Known Activations