© 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. 30800
    Prev
    Next
    INDEX
    Explanations

    phrases related to verification and identification processes in the context of applications, particularly concerning tokens and traffic origination

    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
    #!/
    -0.57
    #
    -0.56
     Exacts
    -0.52
    dormit
    -0.50
     Hij
    -0.49
    raits
    -0.49
    Predicted
    -0.49
    OwnProperty
    -0.48
     details
    -0.47
    AddHtmlAttribute
    -0.47
    POSITIVE LOGITS
     ""],
    0.58
    verwijspagina
    0.57
    XmlRootElement
    0.54
     solares
    0.52
     garrafa
    0.52
    lane
    0.51
    солю
    0.51
     âges
    0.51
     végétale
    0.51
    Viited
    0.50
    Activations Density 0.141%

    No Known Activations