© 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. 17709
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or operators associated with addition

    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
    complexContent
    -0.83
    LookAnd
    -0.79
     vPvB
    -0.77
    septic
    -0.77
    jsii
    -0.74
    pushFollow
    -0.73
    nasium
    -0.73
    DebuggerNonUser
    -0.71
     Baillargeon
    -0.71
    setVerticalGroup
    -0.69
    POSITIVE LOGITS
     humains
    0.65
     terminée
    0.61
     pouvaient
    0.60
     fédé
    0.59
     NotImplemented
    0.58
     intitulée
    0.57
     insectes
    0.56
     humaines
    0.56
     démocr
    0.55
     portata
    0.55
    Activations Density 0.003%

    No Known Activations