© 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. 8394
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or programming notation involving tildes

    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
    overline
    -0.81
     Mors
    -0.80
    fontawesome
    -0.75
     Jacobs
    -0.72
    квар
    -0.72
     Harrington
    -0.71
     GridLayout
    -0.71
     Massa
    -0.70
    kops
    -0.70
     Ress
    -0.69
    POSITIVE LOGITS
    tilde
    1.38
     nahilalakip
    0.81
     GTP
    0.81
     LDA
    0.77
     Schild
    0.76
     CHtml
    0.74
    SourceChecksum
    0.73
    PyExc
    0.71
     Hæ
    0.71
     Pard
    0.70
    Activations Density 0.022%

    No Known Activations