© 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. 17489
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and their corresponding outcomes

    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
    ArrowToggle
    -0.74
    ValueStyle
    -0.67
     contextLoads
    -0.67
    Rüyada
    -0.59
     eventdata
    -0.56
     Jurí
    -0.54
    bootstrapcdn
    -0.54
     Tabor
    -0.54
    AutoScaleMode
    -0.53
     colectiva
    -0.53
    POSITIVE LOGITS
     للاسماء
    0.60
    ">//
    0.48
    Véxase
    0.47
    ">)</
    0.46
    Jîn
    0.45
     sundry
    0.45
     ['./
    0.44
     Parkway
    0.44
    Tazama
    0.44
    LayoutStyle
    0.44
    Activations Density 0.004%

    No Known Activations