© 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. 15424
    Prev
    Next
    INDEX
    Explanations

    specific codes or identifiers related to data formats or programming functions

    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
     at
    -0.41
    了吧
    -0.41
    ,
    -0.40
    的吧
    -0.40
     no
    -0.40
     save
    -0.40
     
    -0.38
     At
    -0.37
     we
    -0.36
    fonds
    -0.36
    POSITIVE LOGITS
    AccessorTable
    1.02
     صوتيه
    1.02
    ⓧ
    1.00
    extAlignment
    0.92
    urlpatterns
    0.89
     '\\;'
    0.89
    IntoConstraints
    0.87
    IsContent
    0.87
    GOTREF
    0.86
    twimg
    0.86
    Activations Density 0.006%

    No Known Activations