© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 12054
    Prev
    Next
    INDEX
    Explanations

    instances of the word "solve" and related forms 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
     answers
    -0.85
     replies
    -0.78
    solutions
    -0.73
    Answer
    -0.72
     solutions
    -0.69
    Solutions
    -0.68
    er
    -0.67
    answers
    -0.65
     respondió
    -0.65
     answer
    -0.65
    POSITIVE LOGITS
     Stove
    0.81
     Siv
    0.76
    bufio
    0.73
    /***/
    0.72
     defaultstate
    0.71
    setopt
    0.71
     stove
    0.70
    bukkit
    0.69
    Colt
    0.68
     GenerationType
    0.67
    Activations Density 0.022%

    No Known Activations