© 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. 12-RES-MATRYOSHKA-DC
    7. 21039
    Prev
    Next
    INDEX
    Explanations

    file path or directory references

    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
    Negative Logits
    Clik
    -0.78
     Construcción
    -0.74
    enumii
    -0.74
    jsonwebtoken
    -0.72
     itſelf
    -0.72
     Monfieur
    -0.72
     ―――――
    -0.71
     againſt
    -0.69
     Anſ
    -0.69
     myſelf
    -0.68
    POSITIVE LOGITS
    GEBURTSDATUM
    0.68
     &___
    0.66
    AndEndTag
    0.62
    IntoConstraints
    0.54
    :✨
    0.52
     ComVisible
    0.51
    kes
    0.47
     население
    0.47
    FieldDescriptor
    0.46
     ole
    0.46
    Activations Density 0.006%

    No Known Activations