© 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. 22-RES-MATRYOSHKA-DC
    7. 2888
    Prev
    Next
    INDEX
    Explanations

    scientific language describing biological processes

    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
    ädie
    -0.51
     Vorsch
    -0.47
    اديم
    -0.47
    ⓧ
    -0.46
    Архівовано
    -0.46
     booth
    -0.43
    laq
    -0.42
    inchilla
    -0.42
    Ciri
    -0.41
     Publikum
    -0.40
    POSITIVE LOGITS
     hormones
    0.73
     Viruses
    0.73
     viruses
    0.72
     Hormones
    0.71
    poptosis
    0.71
     RNA
    0.70
     DNA
    0.69
     rRNA
    0.68
     antibiotics
    0.67
     Virus
    0.66
    Activations Density 1.175%

    No Known Activations