© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 22570
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical names and their relationships to treatments and conditions

    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
     mix
    -0.57
     Ar
    -0.57
     Man
    -0.54
     Re
    -0.53
     Mor
    -0.52
    Ar
    -0.52
     Mon
    -0.52
     te
    -0.51
     Y
    -0.50
    ')));
    -0.50
    POSITIVE LOGITS
    InputBorder
    0.77
     Anſ
    0.75
     مرئيه
    0.75
     ―――――
    0.74
    protoimpl
    0.74
    expandindo
    0.72
     باخ
    0.71
     pleaſure
    0.69
    abetes
    0.69
    AddTagHelper
    0.69
    Activations Density 0.023%

    No Known Activations