© 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. 28435
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses and related number representations

    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
    ArgsConstructor
    -0.90
     Normdatei
    -0.73
    ViewFeatures
    -0.67
    ########.
    -0.64
     متعلقه
    -0.64
    principalColumn
    -0.62
     مرئيه
    -0.60
    Personendaten
    -0.59
    riwal
    -0.59
    IsMutable
    -0.57
    POSITIVE LOGITS
    antMatchers
    0.67
    Véase
    0.52
     EventEmitter
    0.51
    تمبر
    0.51
    ázaro
    0.51
    jsdelivr
    0.51
    osé
    0.49
     wireType
    0.49
    ември
    0.49
    Viernes
    0.49
    Activations Density 0.003%

    No Known Activations