© 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. 12-RES-MATRYOSHKA-DC
    7. 376
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their relationships or interactions within the text

    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
     cauſe
    -0.79
     pleaſure
    -0.79
     Rasul
    -0.77
     epä
    -0.77
    ."</
    -0.75
    betic
    -0.74
    ERTY
    -0.74
     ſur
    -0.73
     defaultstate
    -0.73
    AccessFile
    -0.73
    POSITIVE LOGITS
     him
    1.00
     them
    0.90
     Him
    0.81
    Him
    0.75
     THEM
    0.73
     Them
    0.71
     her
    0.70
    Them
    0.67
    him
    0.66
     виправивши
    0.66
    Activations Density 1.045%

    No Known Activations