© 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. 2734
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical constructs, particularly involving matrices and variances

    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
    },[])
    -0.52
     progress
    -0.42
    oral
    -0.41
    bart
    -0.41
     Wage
    -0.41
     provoquer
    -0.40
     Con
    -0.40
    poved
    -0.40
     Cohen
    -0.39
     salarios
    -0.39
    POSITIVE LOGITS
    StructEnd
    1.05
    Portale
    0.82
    сылкі
    0.81
     itſelf
    0.75
    TypedDataSet
    0.73
    ISupport
    0.70
    TagMode
    0.70
    脚注の使い方
    0.70
     betweenstory
    0.69
     domes
    0.69
    Activations Density 0.750%

    No Known Activations