© 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. 14714
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols representing sets or variables in formal mathematical expressions

    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
     Bernal
    -0.68
     }^{(
    -0.65
     Torrance
    -0.63
    dum
    -0.63
     Passion
    -0.62
    [\
    -0.61
    <strong>
    -0.60
    jl
    -0.58
     Baths
    -0.58
     sterili
    -0.58
    POSITIVE LOGITS
     متعلقه
    1.03
    ########.
    0.91
     disambiguazione
    0.84
     فريبيس
    0.82
     <=",
    0.82
    données
    0.78
    AccessorTable
    0.76
    конец
    0.76
    ISSE
    0.75
    SourceChecksum
    0.75
    Activations Density 0.028%

    No Known Activations