© 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. 2714
    Prev
    Next
    INDEX
    Explanations

    words with prefixes or suffixes, often related to medicine, finance, or scientific study

    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
     Jefus
    -0.98
     itſelf
    -0.98
     purpoſe
    -0.97
     Diſ
    -0.96
     Majefty
    -0.95
     Monfieur
    -0.95
     Reſ
    -0.93
     ſta
    -0.92
     pleaſure
    -0.91
     himſelf
    -0.91
    POSITIVE LOGITS
    BindingResult
    0.50
     onPostExecute
    0.49
     impuestos
    0.44
    道を
    0.42
     к
    0.42
     culturali
    0.41
    innerText
    0.41
    ್
    0.41
     с
    0.41
    ی
    0.40
    Activations Density 0.553%

    No Known Activations