© 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. 11354
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and experimental processes

    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
     Reſ
    -0.62
    JsonIgnore
    -0.60
    BuildContext
    -0.58
     quæ
    -0.58
     iſt
    -0.57
     ſeveral
    -0.56
    =$?
    -0.55
     Anſ
    -0.55
    schild
    -0.55
     reaſon
    -0.54
    POSITIVE LOGITS
    InitVars
    0.57
    Välislingid
    0.52
    Gambas
    0.50
     EconPapers
    0.48
    GraphicsUnit
    0.47
    ährlich
    0.46
    ConstraintMaker
    0.45
    HideFlags
    0.44
     perfect
    0.43
     put
    0.43
    Activations Density 0.751%

    No Known Activations