© 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. 26084
    Prev
    Next
    INDEX
    Explanations

    medical and biological terminology related to cancer prognosis and exposure to toxins

    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
    mybatisplus
    -0.94
     pinulongan
    -0.92
    enumi
    -0.85
    expandindo
    -0.83
    GEBURTSDATUM
    -0.82
    ContentAsync
    -0.80
     مرئيه
    -0.80
    ⓧ
    -0.78
    XMLSchema
    -0.77
    enterOuterAlt
    -0.75
    POSITIVE LOGITS
    erre
    0.45
    довой
    0.44
    jà
    0.43
    tok
    0.42
     schon
    0.41
     and
    0.40
     sä
    0.39
     der
    0.39
     voll
    0.39
     I
    0.39
    Activations Density 0.084%

    No Known Activations