© 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. 455
    Prev
    Next
    INDEX
    Explanations

    code formatting characters preceding code

    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
     }</
    -0.72
    )=>{
    -0.71
     /
    -0.71
     //
    -0.70
    (!__
    -0.69
     ${
    -0.69
     ?>
    -0.68
    }}],
    -0.68
     und
    -0.66
     #
    -0.66
    POSITIVE LOGITS
     itſelf
    1.29
     myſelf
    1.25
     doubtnut
    1.07
     Anſ
    1.05
     Jefus
    0.99
     pleaſure
    0.98
     Houſe
    0.97
     Monfieur
    0.97
     himſelf
    0.96
     ་་
    0.93
    Activations Density 1.818%

    No Known Activations