© 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. 12-RES-MATRYOSHKA-DC
    7. 32224
    Prev
    Next
    INDEX
    Explanations

    the presence of the string "EN"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     EconPapers
    -0.84
    ğiniz
    -0.59
     ?>/
    -0.57
     musicales
    -0.55
     ويكيميديا
    -0.54
    RenderAtEndOf
    -0.53
    ńcz
    -0.52
     inconn
    -0.52
    //
    -0.52
    forRoot
    -0.51
    POSITIVE LOGITS
    EN
    0.85
    kloped
    0.69
    ValueStyle
    0.66
     EN
    0.64
    PerformLayout
    0.63
     mainland
    0.59
     myſelf
    0.59
     Reſ
    0.59
    ForValue
    0.57
     Diſ
    0.57
    Activations Density 0.000%

    No Known Activations