© 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. 26536
    Prev
    Next
    INDEX
    Explanations

    instances of the word "username."

    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
    reportWebVitals
    -1.05
     disambiguazione
    -0.98
     AssemblyCulture
    -0.96
    ValueStyle
    -0.87
     betweenstory
    -0.84
     Magno
    -0.82
    Geplaatst
    -0.79
    antaranya
    -0.79
     BTU
    -0.79
     Causeway
    -0.79
    POSITIVE LOGITS
    setUsername
    1.20
    getUsername
    1.18
    username
    1.17
     getUsername
    1.16
    Username
    1.13
     username
    1.09
     Username
    0.96
    USERNAME
    0.94
     setUsername
    0.89
    ByUsername
    0.81
    Activations Density 0.002%

    No Known Activations