© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21778
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical proofs and structures

    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
    NameInMap
    -0.47
    runApp
    -0.46
    oneof
    -0.46
    imaan
    -0.43
    XmlAccessType
    -0.43
    )))
    -0.40
    actionMode
    -0.40
    )}
    -0.39
    }}}
    -0.39
     Conférence
    -0.38
    POSITIVE LOGITS
    OCCURRED
    0.68
    клопе
    0.66
    TagMode
    0.65
     Diri
    0.64
    RenderAtEndOf
    0.63
     kaynağından
    0.61
    Portail
    0.60
    Clik
    0.59
    بوابة
    0.59
     civilisation
    0.58
    Activations Density 0.092%

    No Known Activations