© 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. 1158
    Prev
    Next
    INDEX
    Explanations

    the word "work" and variations thereof

    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
    HtmlAttribute
    -0.59
    NoSuchAlgorithm
    -0.56
    Datuak
    -0.56
    èces
    -0.56
    JsonInclude
    -0.55
    nictví
    -0.52
     BrowserModule
    -0.52
    InputBorder
    -0.52
     gev
    -0.51
    lıyor
    -0.51
    POSITIVE LOGITS
     hard
    0.92
     harder
    0.78
    hard
    0.76
     ethic
    0.75
     wonders
    0.73
     Hard
    0.72
    horse
    0.71
    Hard
    0.70
     hardest
    0.69
    aday
    0.63
    Activations Density 0.475%

    No Known Activations