© 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. 410
    Prev
    Next
    INDEX
    Explanations

    words related to coding and computer memory

    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
     femininos
    -0.90
     abstrato
    -0.81
     femininas
    -0.81
     '\\;'
    -0.79
     originais
    -0.79
     isolado
    -0.79
     vermelhas
    -0.78
     traseiro
    -0.77
     engraçadas
    -0.77
    OGND
    -0.75
    POSITIVE LOGITS
     em
    0.51
     mais
    0.46
     das
    0.46
     bem
    0.45
     ao
    0.45
     uma
    0.45
     medal
    0.44
     ou
    0.44
     o
    0.42
     um
    0.42
    Activations Density 0.959%

    No Known Activations