© 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. 15490
    Prev
    Next
    INDEX
    Explanations

    identifiers related to mathematical expressions and variables

    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
     oprot
    -0.54
    parent
    -0.50
    xtick
    -0.50
    AndEndTag
    -0.50
     pagare
    -0.49
     padres
    -0.48
    awtextra
    -0.47
     bassi
    -0.47
     '@/
    -0.47
     mapStateToProps
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.65
     صوتيه
    0.63
     GenerationType
    0.61
    DoubleQuotes
    0.59
     uintptr
    0.59
    </tfoot>
    0.57
     তারিখ
    0.57
     AssemblyTitle
    0.56
    modelBuilder
    0.54
    )))));
    0.54
    Activations Density 0.063%

    No Known Activations