© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 232
    Prev
    Next
    INDEX
    Explanations

    prefixes such as "inter-", "un-", "pre-", "post-", "dis-", and "pro-"

    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
    scienti
    -0.84
    étoit
    -0.82
    unpublished
    -0.81
    oltre
    -0.81
    FTFY
    -0.80
    símbolo
    -0.79
    nościo
    -0.77
    slavery
    -0.77
     feroit
    -0.77
    lijck
    -0.77
    POSITIVE LOGITS
    -
    0.84
    pro
    0.70
    -/
    0.70
    -​
    0.64
    set
    0.60
    -“
    0.59
    app
    0.57
    par
    0.57
    class
    0.57
    conf
    0.56
    Activations Density 1.157%

    No Known Activations