© 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. 22-RES-MATRYOSHKA-DC
    7. 282
    Prev
    Next
    INDEX
    Explanations

    scientific literature about gene expression and cancer

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    出版年
    -0.66
    enumi
    -0.56
     dites
    -0.54
    bootstrapcdn
    -0.54
    Пусть
    -0.54
     Anything
    -0.51
     every
    -0.50
    את
    -0.50
     Everything
    -0.49
    ◀
    -0.48
    POSITIVE LOGITS
    increased
    0.82
    Increased
    0.81
     Increased
    0.77
     increased
    0.76
    INCRE
    0.75
    Kesimpulan
    0.69
    ]")]
    0.68
    Differences
    0.68
     addition
    0.67
    addition
    0.67
    Activations Density 2.635%

    No Known Activations