© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21596
    Prev
    Next
    INDEX
    Explanations

    terms related to raw data and data values in research 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
     AssemblyCompany
    -0.80
    Portail
    -0.77
     GetEnumerator
    -0.77
    ={`/
    -0.73
     <=",
    -0.71
     AssemblyVersion
    -0.70
    ParallelGroup
    -0.70
    uatu
    -0.69
     daripada
    -0.68
    Portale
    -0.68
    POSITIVE LOGITS
     Raw
    1.53
     RAW
    1.47
    Raw
    1.40
    RAW
    1.36
     raw
    1.30
    raw
    1.24
    getRaw
    1.02
    RawData
    1.02
    rawData
    0.96
    rawQuery
    0.87
    Activations Density 0.007%

    No Known Activations