© 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. 4793
    Prev
    Next
    INDEX
    Explanations

    phrases related to classifications, definitions, and comparisons

    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
    AndEndTag
    -0.77
     AssemblyCompany
    -0.63
    IVEREF
    -0.62
     Kuru
    -0.61
    HostException
    -0.59
     entanto
    -0.59
    putstr
    -0.58
    Coro
    -0.57
    digm
    -0.57
     IndexError
    -0.56
    POSITIVE LOGITS
    onomía
    0.61
    évaluateur
    0.60
    الإنجليزية
    0.60
    RTEE
    0.60
    下载附件
    0.56
     препратки
    0.54
    BeginContext
    0.51
    makeText
    0.50
     treated
    0.49
     Treated
    0.49
    Activations Density 0.697%

    No Known Activations