© 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. 30008
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions of equality

    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
    -0.73
     raiſ
    -0.69
     myſelf
    -0.67
     ſtand
    -0.59
     uſed
    -0.58
    StateToProps
    -0.58
     Conſ
    -0.58
     juſt
    -0.58
     corresponde
    -0.57
    ocracy
    -0.57
    POSITIVE LOGITS
    رشف
    0.82
     ModelExpression
    0.77
    MemoryWarning
    0.76
    GEBURTSDATUM
    0.76
    OrNil
    0.72
     CreateTagHelper
    0.71
    الإنجليزية
    0.71
    queryInterface
    0.70
    endsection
    0.69
    PYX
    0.64
    Activations Density 0.009%

    No Known Activations