© 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. 19760
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or formulas related to matrix operations and their properties

    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
     tartalomajánló
    -0.63
    __':
    -0.57
    )}-\
    -0.56
     ©️
    -0.56
    FTFY
    -0.56
    EXHIBIT
    -0.56
    })-\
    -0.53
    ()])
    -0.52
    idios
    -0.52
     surla
    -0.52
    POSITIVE LOGITS
    Géographie
    0.55
    NavController
    0.52
    躇
    0.52
    enschappen
    0.50
     ActivatedRoute
    0.50
     useCallback
    0.50
    ForRow
    0.49
    nonatomic
    0.49
    tanto
    0.48
     Breeze
    0.48
    Activations Density 0.054%

    No Known Activations