© 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. 28322
    Prev
    Next
    INDEX
    Explanations

    references to structural models and types in scientific or technical contexts

    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
     purpoſe
    -0.93
     myſelf
    -0.81
    Datuak
    -0.81
     himſelf
    -0.80
     ſtate
    -0.77
     raiſ
    -0.77
     itſelf
    -0.75
     themſelves
    -0.74
     diſt
    -0.74
     houſe
    -0.74
    POSITIVE LOGITS
    Inflater
    0.56
    raszam
    0.55
    }{*}{
    0.54
    :]:
    0.53
    tonsoft
    0.52
     Exacts
    0.51
    ########.
    0.51
    }\]
    0.51
    Eloquent
    0.50
    asmussen
    0.50
    Activations Density 0.001%

    No Known Activations