Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 10713
    Prev
    Next
    INDEX
    Explanations

    references to academic contributions and acknowledgments in research

    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
    +:+
    -0.56
    SPJ
    -0.45
    nasse
    -0.44
    ])));
    -0.43
     around
    -0.43
    chan
    -0.43
     interna
    -0.42
    och
    -0.42
    tapa
    -0.41
    大家好
    -0.41
    POSITIVE LOGITS
     متعلقه
    1.05
     nahilalakip
    0.99
     EconPapers
    0.90
    +#+#
    0.89
     kasarigan
    0.78
     HttpNotFound
    0.77
     TextInputType
    0.75
    enumi
    0.74
     BoxDecoration
    0.71
    MLLoader
    0.71
    Activations Density 0.011%

    No Known Activations