© 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. 8473
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structures

    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
     itſelf
    -1.12
     themſelves
    -1.00
     himſelf
    -0.99
     Chriftian
    -0.96
     Diſ
    -0.93
     uſed
    -0.88
     myſelf
    -0.87
     Efq
    -0.86
     poffible
    -0.85
     reaſon
    -0.84
    POSITIVE LOGITS
     the
    0.95
     a
    0.73
     an
    0.71
     super
    0.69
     this
    0.63
    wixt
    0.59
     my
    0.58
     some
    0.58
    larak
    0.58
     its
    0.57
    Activations Density 0.125%

    No Known Activations