© 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. 25592
    Prev
    Next
    INDEX
    Explanations

    references to sin and related concepts

    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
     للاسماء
    -1.17
     Reſ
    -1.11
    "):
    -1.09
     AssemblyCompany
    -1.06
    ')):
    -1.06
    ſelf
    -1.05
     myſelf
    -1.05
     Monfieur
    -1.05
     themſelves
    -1.02
    ')")
    -1.02
    POSITIVE LOGITS
     sin
    1.16
     Sinha
    1.12
     SIN
    1.11
    sin
    1.09
     Sin
    1.04
     sins
    1.03
     Sinclair
    1.02
    Sin
    1.00
     Sins
    0.86
    SIN
    0.84
    Activations Density 0.021%

    No Known Activations