© 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. 3375
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions involving variables and constants

    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
     كومونز
    -0.54
    Hochspringen
    -0.53
    enderror
    -0.51
    ḏ
    -0.50
     sch
    -0.50
     تانيه
    -0.50
    Inference
    -0.47
    MenuList
    -0.47
     cal
    -0.46
    neer
    -0.46
    POSITIVE LOGITS
     مشين
    0.66
    adaptiveStyles
    0.63
     houſe
    0.61
     uſe
    0.60
     purpoſe
    0.59
     uſed
    0.59
     preſent
    0.59
     ſtate
    0.58
     faſt
    0.56
     chofe
    0.55
    Activations Density 0.306%

    No Known Activations