© 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. 31090
    Prev
    Next
    INDEX
    Explanations

    references to scientific papers and their contents, particularly in the field of physics

    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
     estimés
    -0.64
    multer
    -0.63
    httphttps
    -0.63
     iprot
    -0.60
     AssemblyCulture
    -0.59
    Portail
    -0.57
    ыгана
    -0.57
    AndEndTag
    -0.57
    EndContext
    -0.56
     mondial
    -0.56
    POSITIVE LOGITS
     bezeichneter
    0.54
     incendios
    0.54
     varandra
    0.52
    μφ
    0.51
    |^
    0.51
     Fehl
    0.51
    isnan
    0.50
    «<
    0.49
    ]]
    0.49
     onts
    0.48
    Activations Density 0.004%

    No Known Activations