© 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. 18448
    Prev
    Next
    INDEX
    Explanations

    terminators and transitions in mathematical arguments or proofs

    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
    ########.
    -0.86
     Jefus
    -0.66
     Theſe
    -0.65
    parsedMessage
    -0.62
     raiſ
    -0.60
     通販
    -0.59
     leſs
    -0.57
     juſt
    -0.55
     siku
    -0.54
     itſelf
    -0.54
    POSITIVE LOGITS
    InputBorder
    0.63
    icoot
    0.57
     PhpStorm
    0.53
     BrowserRouter
    0.52
    RectangleBorder
    0.52
     useRef
    0.50
    appcompat
    0.48
     estimé
    0.47
    ísica
    0.47
    bcrypt
    0.46
    Activations Density 0.040%

    No Known Activations