© 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. 2634
    Prev
    Next
    INDEX
    Explanations

    legal and scientific publications.

    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
     للمعارف
    -0.57
    tagHelperRunner
    -0.56
    rawDesc
    -0.56
    みに
    -0.49
    PerformLayout
    -0.48
    üenza
    -0.46
    rítica
    -0.44
    ãi
    -0.42
     HomeComponent
    -0.42
    COUVER
    -0.41
    POSITIVE LOGITS
     number
    2.13
     No
    1.91
     Number
    1.83
    number
    1.78
    No
    1.71
     numbers
    1.70
     NUMBER
    1.63
    Number
    1.62
     número
    1.61
     no
    1.53
    Activations Density 0.405%

    No Known Activations