© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4201
    Prev
    Next
    INDEX
    Explanations

    terms related to accumulation and its various forms in different contexts

    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
     Janes
    -0.79
     Meksiku
    -0.72
    azon
    -0.64
     foramen
    -0.62
    Fprintf
    -0.62
     raz
    -0.61
     MotionEvent
    -0.61
    useNewUrlParser
    -0.60
    atyana
    -0.60
    DOCTYPE
    -0.60
    POSITIVE LOGITS
     accumulation
    1.41
     accumulations
    1.35
     accumulate
    1.30
     Accum
    1.29
     accumulating
    1.27
    accumulation
    1.25
     Accumulation
    1.24
     accumulated
    1.23
    accum
    1.20
     accumulates
    1.17
    Activations Density 0.055%

    No Known Activations