© 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. 32248
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to matrix operations and algebraic 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
    Rptr
    -0.61
     sconto
    -0.60
     grève
    -0.59
     spéciale
    -0.58
    PreExecute
    -0.58
     organised
    -0.57
     cadeaux
    -0.57
     médicaux
    -0.56
     Sociales
    -0.56
    odotus
    -0.55
    POSITIVE LOGITS
    DebuggerNonUser
    0.67
    rungsseite
    0.65
     تضيفلها
    0.64
    mtable
    0.53
     inst
    0.53
     للمعارف
    0.52
    malade
    0.51
    ตรี
    0.50
    Rhestr
    0.50
     ويكيپيديا
    0.49
    Activations Density 0.007%

    No Known Activations