© 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. 15434
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to equality and conditions

    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
    PYX
    -0.65
    WebServlet
    -0.54
    Gambas
    -0.50
     embri
    -0.47
    ärä
    -0.46
     beginnetje
    -0.46
     LEYENDO
    -0.45
    atars
    -0.45
    iotensin
    -0.45
     crossorigin
    -0.45
    POSITIVE LOGITS
    Personendaten
    0.73
    SourceChecksum
    0.64
    Espèce
    0.63
    mello
    0.57
     EconPapers
    0.55
     >=",
    0.54
    kloped
    0.54
     resourceCulture
    0.53
     GUS
    0.53
    ритори
    0.53
    Activations Density 0.053%

    No Known Activations