Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 22577
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "thick" in various contexts

    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
    fulness
    -0.74
     stress
    -0.62
     quanto
    -0.61
    lama
    -0.59
    stress
    -0.58
     &&
    
    -0.58
    tabular
    -0.57
     Tash
    -0.57
    ranza
    -0.56
     perman
    -0.56
    POSITIVE LOGITS
    thick
    0.96
     thickened
    0.96
     thicken
    0.96
     thickening
    0.94
     Thick
    0.93
    Thick
    0.91
     thick
    0.89
     Griswold
    0.88
     thicket
    0.84
     épais
    0.82
    Activations Density 0.003%

    No Known Activations