© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11125
    Prev
    Next
    INDEX
    Explanations

    instances of the word "improvement" and its variations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     HasFactory
    -0.80
    ter
    -0.70
    ers
    -0.70
    cher
    -0.67
    RRect
    -0.66
    aly
    -0.65
     Bous
    -0.64
    posób
    -0.64
    posedge
    -0.63
    Gtk
    -0.60
    POSITIVE LOGITS
    Improvement
    0.81
     Krie
    0.80
     Improvement
    0.79
     Improvements
    0.76
     AssemblyTitle
    0.75
    jspb
    0.74
    smiley
    0.72
    ajaran
    0.71
    ysacchar
    0.71
    isiaj
    0.71
    Activations Density 0.022%

    No Known Activations