© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 3171
    Prev
    Next
    INDEX
    Explanations

    code examples with associative arrays and variable assignments

    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
    Negative Logits
    TargetException
    -0.58
    uertos
    -0.50
    ErrorListener
    -0.50
    felde
    -0.48
    thol
    -0.47
     Honor
    -0.46
     wireType
    -0.45
     sitten
    -0.45
    txtName
    -0.44
    viedo
    -0.44
    POSITIVE LOGITS
     unique
    1.54
     Unique
    1.46
    unique
    1.41
    Unique
    1.38
     uniqueness
    1.26
     UNIQUE
    1.23
     uniquely
    1.20
    UNIQUE
    1.14
     unik
    1.09
     uniques
    1.08
    Activations Density 0.691%

    No Known Activations