© 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. 25689
    Prev
    Next
    INDEX
    Explanations

    numeric data and values related to scientific measurements

    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
     propOrder
    -0.75
     Michal
    -0.65
     betweenstory
    -0.64
     Handy
    -0.62
    RectangleBorder
    -0.61
    Michal
    -0.60
    Chara
    -0.60
    Buc
    -0.59
    SNA
    -0.59
     druck
    -0.58
    POSITIVE LOGITS
     ​​
    0.78
    DOCTYPE
    0.71
    Wolfgang
    0.62
    CJK
    0.62
    acamata
    0.60
    SerializedSize
    0.60
    doctype
    0.60
    mergeFrom
    0.60
    LOOKUP
    0.59
     Bayard
    0.59
    Activations Density 0.095%

    No Known Activations