© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 183
    Prev
    Next
    INDEX
    Explanations

    numbers, especially those related to technical specifications or references

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    ../../../
    -0.75
     Walkover
    -0.71
     Pues
    -0.70
    BibitemShut
    -0.69
    antaine
    -0.69
     esternos
    -0.69
    Diweddarwch
    -0.68
    omiast
    -0.68
     Forse
    -0.66
    TypedDataSet
    -0.65
    POSITIVE LOGITS
    rd
    1.59
    GPP
    0.89
     rd
    0.84
    rds
    0.74
    RD
    0.71
     FormBuilder
    0.67
    ßig
    0.64
    quarters
    0.61
     '{@
    0.61
    prnewswire
    0.60
    Activations Density 2.828%

    No Known Activations